# PlungeAI

> Developer documentation for the PlungeAI One API, the MCP server and the agent skills.

- [PlungeAI API Overview](https://www.plungeai.com/docs/getting-started/overview.md): Connect PlungeAI to your coding agent, onboard it, and build on the One API and the MCP server.
- [Choose an API](https://www.plungeai.com/docs/getting-started/choose-an-api.md): Find the right PlungeAI API for what you are building.
- [PlungeAI API Pricing](https://www.plungeai.com/docs/getting-started/pricing.md): How PlungeAI bills model calls: the wallet, the three prices, and the posted price list.
- [API Rate Limits](https://www.plungeai.com/docs/getting-started/rate-limits.md): Default limits: execution planes 30 to 300 per minute by tier, models plane 600 per minute per key.
- [Your first calls](https://www.plungeai.com/docs/getting-started/quickstart.md): One key, one agent call, one model call, one MCP connection.
- [Authentication & keys](https://www.plungeai.com/docs/getting-started/authentication.md): The one key, which routes accept it, and how to keep it safe.
- [How PlungeAI works](https://www.plungeai.com/docs/getting-started/concepts.md): The seven planes, the MCP endpoint and how a request flows.
- [Models Plane Quickstart](https://www.plungeai.com/docs/models/quickstart.md): OpenAI-compatible chat completions with one `ozk_` key and a base-URL swap. (planned)
- [Models Best Practices](https://www.plungeai.com/docs/models/best-practices.md): Request fields, tools and structured output, and what each provider supports. (planned)
- [Evaluating Models](https://www.plungeai.com/docs/models/evaluating-models.md): Planned: compare models on your own gold set, with cost and latency. (planned)
- [Routing: models, sort, failover](https://www.plungeai.com/docs/models/routing.md): Ordered fallback with `models[]`, `sort` by price, latency or throughput, and presets. (planned)
- [Migrate to PlungeAI](https://www.plungeai.com/docs/models/migrate.md): Move from OpenRouter, the OpenAI SDK, LiteLLM or the Vercel AI SDK. (planned)
- [Anthropic Messages API](https://www.plungeai.com/docs/models/anthropic-messages.md): Point the Anthropic SDK or Claude Code at PlungeAI. Any model through the Messages API, on the same routing, guardrails and billing as chat completions.
- [Advanced Models Settings](https://www.plungeai.com/docs/models/advanced-settings.md): Guardrails, the opt-in response cache and BYOK-or-billed routing. (planned)
- [Upgrade from guide 2.0 to 3.0](https://www.plungeai.com/docs/models/migration-guide.md): What changed between the 2.0 and 3.0 developer guides, for every plane. (planned)
- [Embeddings Quickstart](https://www.plungeai.com/docs/models/embeddings.md): OpenAI-compatible embeddings (`openai/*` models only). (planned)
- [Models, providers and slugs](https://www.plungeai.com/docs/models/catalog.md): Every routable model with context, list and Ocean price per 1M tokens, % off and capabilities.
- [Models Billing & Metering](https://www.plungeai.com/docs/models/billing.md): Account status, price = cost × org markup, reserve-then-settle, spend caps. (planned)
- [Models Streaming](https://www.plungeai.com/docs/models/streaming.md): SSE chat completions, translated for non-OpenAI providers. (planned)
- [Workflows Quickstart](https://www.plungeai.com/docs/workflows/quickstart.md): Run multi-agent CNL workflows inline or saved, sync or streamed. (planned)
- [Workflow Best Practices](https://www.plungeai.com/docs/workflows/best-practices.md): Write CNL that validates, runs, and fails loudly. (planned)
- [The CNL workflow spec](https://www.plungeai.com/docs/workflows/core-concepts/cnl.md): Workflow structure, task types and validation rules. (planned)
- [Choosing agents and models](https://www.plungeai.com/docs/workflows/core-concepts/agents-and-models.md): Agent tiers, model pinning, and how much time parallel fan-out takes. (planned)
- [Workflow Runs Lifecycle](https://www.plungeai.com/docs/workflows/core-concepts/run-lifecycle.md): Create a run, read its status and result, cancel it. (planned)
- [Results and traces](https://www.plungeai.com/docs/workflows/core-concepts/results-and-traces.md): What a run returns and how to read its persisted trace. (planned)
- [Follow-ups and continuation](https://www.plungeai.com/docs/workflows/core-concepts/follow-ups.md): Chain a run with follow-ups and answer paused runs. (planned)
- [Interactive Chat](https://www.plungeai.com/docs/workflows/examples/chat.md): A multi-turn chat session over MCP. (planned)
- [Deep Research](https://www.plungeai.com/docs/workflows/examples/deep-research.md): A goal-driven research workflow that answers with sources. (planned)
- [Batch Enrichment](https://www.plungeai.com/docs/workflows/examples/enrichment.md): Enrich a list of items with a `type: batch` workflow, then run it to completion. (planned)
- [Workflow Webhooks](https://www.plungeai.com/docs/workflows/webhooks.md): Planned: get notified when a run finishes. (planned)
- [Parallel and batch tasks](https://www.plungeai.com/docs/workflows/parallel-tasks.md): Fan out with `type: parallel` and run a per-item pipeline with `type: batch`. (planned)
- [Generate a workflow from a goal](https://www.plungeai.com/docs/workflows/generate.md): `plungeai_build_workflow` turns a goal into CNL YAML. (planned)
- [Workflow streaming events](https://www.plungeai.com/docs/workflows/streaming-events.md): SSE engine frames from `execute-stream`. (planned)
- [MCP servers inside workflows](https://www.plungeai.com/docs/workflows/mcp-tool-calling.md): Give a harness task MCP servers to call. (planned)
- [Saved workflows and versions](https://www.plungeai.com/docs/workflows/saved-workflows.md): Save, version and run workflows by id. (planned)
- [Agents Quickstart](https://www.plungeai.com/docs/agents/quickstart.md): Execute a registry agent from a prompt: sync, async or streamed. (planned)
- [Conversations and personas](https://www.plungeai.com/docs/agents/features/conversations.md): Carry context with `messages[]` (partial: `prompt` stays required and threading depends on the agent), `persona`, and MCP `session_id` for reliable threading. (planned)
- [Output formats](https://www.plungeai.com/docs/agents/features/output-formats.md): JSON, YAML, Markdown or text via `format` and `Accept`. (planned)
- [Agent streaming](https://www.plungeai.com/docs/agents/features/streaming.md): OpenAI-shaped chunks with keepalives and `X-Execution-Id`. (planned)
- [Citations](https://www.plungeai.com/docs/agents/features/citations.md): Planned: source annotations on agent answers. (planned)
- [Web search tool agents](https://www.plungeai.com/docs/agents/features/web-search.md): Search the web through registry tool agents. (planned)
- [Outbound MCP runs](https://www.plungeai.com/docs/agents/features/mcp-tools.md): Connect catalog MCP servers to a run and call their tools. (planned)
- [Async execution and results](https://www.plungeai.com/docs/agents/features/async-results.md): `sync:false` returns 202; redeem the result later. (planned)
- [Direct requests](https://www.plungeai.com/docs/agents/examples/direct-requests.md): Ask a question, ask for JSON, send YAML and get Markdown. (planned)
- [Use an agent as a subagent tool](https://www.plungeai.com/docs/agents/examples/subagent.md): Wrap an agent call as a tool in your own orchestrator. (planned)
- [OpenAI compatibility (agents plane)](https://www.plungeai.com/docs/agents/openai-compatibility.md): Which OpenAI request and stream fields the agents plane accepts. (planned)
- [Discovery Quickstart](https://www.plungeai.com/docs/discovery/quickstart.md): Find agents, tools, models, skills and connectors before you call. (planned)
- [Recommend](https://www.plungeai.com/docs/discovery/recommend.md): Ask the registry which capability fits a task. (planned)
- [Search modes and fields](https://www.plungeai.com/docs/discovery/core-concepts/search-modes.md): `mode` hybrid, keyword or vector; `fields` list, summary or full. (planned)
- [The card object](https://www.plungeai.com/docs/discovery/core-concepts/cards.md): What a registry card holds and how to read one. (planned)
- [Card status and kinds](https://www.plungeai.com/docs/discovery/core-concepts/card-status.md): Only `status:active` cards run; kinds you can filter on. (planned)
- [Inspect a tool contract](https://www.plungeai.com/docs/discovery/features/tool-contract.md): Read operations, required params and examples before executing. (planned)
- [Quality signals](https://www.plungeai.com/docs/discovery/features/quality.md): Add `include=quality` to search results. (planned)
- [Catalog resources over MCP](https://www.plungeai.com/docs/discovery/features/resources.md): Dropped: discovery search is synchronous and has no event stream. Replacement: read catalog lists as MCP resources. (planned)
- [Registry kinds](https://www.plungeai.com/docs/discovery/features/kinds.md): Dropped: there is no long-running discovery run to notify on. Replacement: the kinds you can search. (planned)
- [Pagination](https://www.plungeai.com/docs/discovery/features/pagination.md): Discovery search and `GET /v1/tools` page with `limit` and `offset` and return `count`; only `GET /v1/agents` returns `has_more` and `next_offset`. (planned)
- [Workflow templates](https://www.plungeai.com/docs/discovery/features/templates.md): Dropped: a search cannot be cancelled. Replacement: start from a template. (planned)
- [Discovery first](https://www.plungeai.com/docs/discovery/features/discovery-first.md): Dropped: there is no stateful FindAll-style run to refresh. Replacement: the discovery-first rule. (planned)
- [Scheduling Quickstart](https://www.plungeai.com/docs/scheduling/quickstart.md): Cron jobs for agents, queries, workflows and heartbeats. (planned)
- [Run now and run history](https://www.plungeai.com/docs/scheduling/runs.md): Trigger a job now and read its run history. (planned)
- [Webhook triggers](https://www.plungeai.com/docs/scheduling/webhook-triggers.md): Planned: start a job from an inbound webhook on a public host. (planned)
- [Heartbeat check](https://www.plungeai.com/docs/scheduling/examples/heartbeat.md): A heartbeat job that checks a condition and acts on it. (planned)
- [Trigger a workflow or mission](https://www.plungeai.com/docs/scheduling/examples/trigger-workflow.md): Run a workflow or mission on a schedule and notify a channel. (planned)
- [Scheduling: MCP tool → REST API](https://www.plungeai.com/docs/scheduling/migration-guide.md): Planned: move jobs from `plungeai_schedule` to a REST schedules API. (planned)
- [Tools Quickstart](https://www.plungeai.com/docs/tools/quickstart.md): List tool agents, read a contract, execute one operation. (planned)
- [Outcomes and remediation](https://www.plungeai.com/docs/tools/outcomes.md): The seven outcomes, the remediation actions, and their HTTP statuses. (planned)
- [Tool catalog by category](https://www.plungeai.com/docs/tools/catalog.md): The tool agents available today, by category. (planned)
- [Long runs (async)](https://www.plungeai.com/docs/tools/async.md): `mode: "async"` for tool calls that take longer than one request. (planned)
- [Missions Quickstart](https://www.plungeai.com/docs/missions/quickstart.md): Run a bounded agent loop with a goal, allowed tools and an iteration cap. (planned)
- [Mission bounds and the tool fence](https://www.plungeai.com/docs/missions/bounds.md): What a mission may do and where it stops. (planned)
- [Skills, plugins and capability injection](https://www.plungeai.com/docs/missions/capability-injection.md): Inject skills, experts, persona, backgrounds, plugins and MCP. (planned)
- [Pre-built agent cards](https://www.plungeai.com/docs/missions/prebuilt-agents.md): Run a catalog agent card with `mission_ref` or `pack`. (planned)
- [Async missions: the Ten-Minute Relay](https://www.plungeai.com/docs/missions/async-relay.md): Long missions run in resumable legs; poll for the result. (planned)
- [Connectors and connected accounts](https://www.plungeai.com/docs/connectors/quickstart.md): OAuth and API-key connectors, and how a connected account reaches a call. (planned)
- [The connector proxy](https://www.plungeai.com/docs/connectors/proxy.md): Call a provider's API raw through `api.plungeai.com/v1/connect` with your `ozk_` key (`$PLUNGE_API_KEY`). (planned)
- [Traces Quickstart](https://www.plungeai.com/docs/traces/quickstart.md): Read the spans and gateway log of any run by trace id. (planned)
- [Execution history and cost](https://www.plungeai.com/docs/traces/history-and-cost.md): List past runs and what they cost. (planned)
- [The activity log](https://www.plungeai.com/docs/traces/activity-log.md): Your key's call log on the MCP server. (planned)
- [One Agent](https://www.plungeai.com/docs/one-agent/overview.md): One agent id, two modes. One Agent answers once when a task says nothing about looping, and runs a bounded agentic loop when the task carries a turn count.
- [One Agent call mode](https://www.plungeai.com/docs/one-agent/call-mode.md): One model answer from one-agent. The request fields, personas and skills, conversation history, streaming and the response formats.
- [One Agent loop mode](https://www.plungeai.com/docs/one-agent/loop-mode.md): A bounded agentic run on one-agent. The loop command, the tool fence, the mission keys, sessions, approvals and the ways a run stops.
- [One Agent tools](https://www.plungeai.com/docs/one-agent/tools.md): The tools a one-agent loop can call. What a task gets without allowed_tools, the core eight, the other tools and the four bot tools, with what each does and its permission class.
- [One Agent policy and review](https://www.plungeai.com/docs/one-agent/policy-and-review.md): How a one-agent tool call becomes allow, ask or deny, and the safety layers around a run (posture, review, the denial breaker, secret redaction, untrusted-content screening).
- [Bots](https://www.plungeai.com/docs/bots/overview.md): A bot is a saved workflow that runs a One Agent loop on a clock, answers messages, keeps its own memory and files, and stays inside a policy you set.
- [Bot playbook reference](https://www.plungeai.com/docs/bots/playbook-reference.md): Every key a One Agent bot reads, one row each: its type, its default, what it does and which door sets it.
- [Bot schedules and wake](https://www.plungeai.com/docs/bots/schedules-and-wake.md): Give a bot a clock. Cron and one-time schedules from outside or from the bot itself, the wake call, result delivery, the SILENT marker and run history.
- [Bot to bot, groups and A2A](https://www.plungeai.com/docs/bots/bot-to-bot-and-groups.md): How bots talk to each other. The peers fence and message_bot, the inbox and replies, bot groups, and the Agent2Agent doors for outside agents.
- [Bot channels, voice and the chat widget](https://www.plungeai.com/docs/bots/channels-and-voice.md): Talk to a bot from Telegram, WhatsApp, Discord, Teams or Slack. Pairing and bindings, the one-message mention, voice notes, and the embeddable web chat widget.
- [Bot permissions and budget](https://www.plungeai.com/docs/bots/permissions-and-budget.md): What a bot may do and spend. Permission classes and presets, hand-off, admin locks, approvals and their scope, and the per-run and monthly spend caps, applied the same on every door.
- [Bot workspace, inbox and memory](https://www.plungeai.com/docs/bots/workspace-and-inbox.md): What a bot keeps between runs. Its persistent files, the bot-to-bot inbox, and its memory, and how to read each one over REST.
- [Bot triggers and hooks](https://www.plungeai.com/docs/bots/triggers-and-hooks.md): Start a bot from outside with a signed webhook, an email address, a Slack channel, new Gmail or a Git event. Send a bot's run events out through signed hooks. Forward a webhook with no model call.
- [Control a bot over REST, MCP and the CLI](https://www.plungeai.com/docs/bots/rest-mcp-cli.md): Every bot operation on each door. The One API routes, the MCP actions and the Ocean CLI verbs side by side, with the same key, the same rows and the same stored policy.
- [Companies](https://www.plungeai.com/docs/bots/companies.md): A company is a campus of buildings whose offices are workflows. Items walk each building's pipeline, and gates stop them where a person decides.
- [Developer Tools Overview](https://www.plungeai.com/docs/developer-tools/quickstart.md): MCP vs One API vs CLI vs Studio: pick your door. (planned)
- [Account API](https://www.plungeai.com/docs/developer-tools/account-api.md): Planned: manage keys, wallet and usage with a key. Today these live in the Dashboard. (planned)
- [Install PlungeAI Agent Skills](https://www.plungeai.com/docs/developer-tools/agent-skills.md): 31 skills that teach coding agents to use PlungeAI. (planned)
- [Anthropic Tool Calling](https://www.plungeai.com/docs/developer-tools/anthropic-tool-calling.md): Turn PlungeAI tool contracts into Claude tool definitions. (planned)
- [Claude Code Plugin](https://www.plungeai.com/docs/developer-tools/claude-code-plugin.md): The `plungeai` plugin: 31 skills plus its own MCP server config. Install it instead of `claude mcp add`, not in addition. (planned)
- [Ocean CLI](https://www.plungeai.com/docs/developer-tools/cli.md): The `ocean` command: auth, runs, workflows, schedules, registry. (planned)
- [Cursor Plugin](https://www.plungeai.com/docs/developer-tools/cursor-plugin.md): Planned: a Cursor marketplace plugin. (planned)
- [LangChain](https://www.plungeai.com/docs/developer-tools/langchain.md): Use the models plane from LangChain's `ChatOpenAI`. (planned)
- [PlungeAI MCP Server Quickstart](https://www.plungeai.com/docs/developer-tools/mcp/quickstart.md): Connect any MCP client to `https://mcp.plungeai.com/v1`.
- [Programmatic use](https://www.plungeai.com/docs/developer-tools/mcp/programmatic-use.md): Call the MCP server from your own code with raw JSON-RPC, and run outbound MCP servers with `/v1/mcp/runs`. (planned)
- [PlungeAI MCP](https://www.plungeai.com/docs/developer-tools/mcp/plungeai-mcp.md): The one server: install per client, configure, troubleshoot. (planned)
- [Workflows and missions over MCP](https://www.plungeai.com/docs/developer-tools/mcp/workflows-mcp.md): Run workflows and missions from your coding agent, sync or async. (planned)
- [Protocol and transport](https://www.plungeai.com/docs/developer-tools/mcp/protocol.md): Streamable HTTP, JSON-RPC methods, sessions, SSE progress. (planned)
- [Prompts and resources](https://www.plungeai.com/docs/developer-tools/mcp/prompts-resources.md): The `/plungeai` prompt and every `plungeai://` resource. (planned)
- [Move MCP clients from /mcp to /v1](https://www.plungeai.com/docs/developer-tools/mcp/migrate-to-v1.md): `/mcp` is a legacy alias since 2026-09-20; configure `/v1`. (planned)
- [Docs MCP server](https://www.plungeai.com/docs/developer-tools/mcp/docs-mcp.md): Planned: search and read these docs from your agent. (planned)
- [OAuth Provider](https://www.plungeai.com/docs/developer-tools/oauth-provider.md): Planned: sign in with PlungeAI for MCP clients that require OAuth. Today: bearer `ozk_` keys only. (planned)
- [Ollama Tool Calling](https://www.plungeai.com/docs/developer-tools/ollama-tool-calling.md): Turn PlungeAI tool contracts into tool definitions for a local Ollama model through its OpenAI-compatible endpoint. (planned)
- [OpenAI SDK](https://www.plungeai.com/docs/developer-tools/openai-sdk.md): Point the OpenAI Python or TypeScript SDK at PlungeAI. (planned)
- [OpenAI Tool Calling](https://www.plungeai.com/docs/developer-tools/openai-tool-calling.md): Turn tool contracts into OpenAI function definitions and execute the calls. (planned)
- [Generate a client from OpenAPI](https://www.plungeai.com/docs/developer-tools/openapi-codegen.md): Typed clients from `/v1/openapi.json`. (planned)
- [OpenCode Plugin](https://www.plungeai.com/docs/developer-tools/opencode-plugin.md): Connect OpenCode today with an MCP config; a plugin is planned. (planned)
- [@plungeai/one-api](https://www.plungeai.com/docs/sdks/typescript.md): The official TypeScript SDK for the One API — typed resources, streaming, pagination, retries and errors, generated from the OpenAPI document.
- [plungeai (Python)](https://www.plungeai.com/docs/sdks/python.md): The official Python SDK for the One API — sync and async clients, typed resources, streaming, pagination, retries and errors, generated from the OpenAPI document.
- [plungeai-go](https://www.plungeai.com/docs/sdks/go.md): The official Go SDK for the One API — typed resources, streaming, pagination, retries and errors, generated from the OpenAPI document; standard library only.
- [plungeai (Rust)](https://www.plungeai.com/docs/sdks/rust.md): The official Rust SDK for the One API — async client over reqwest, serde-typed resources, streaming, pagination, retries and errors, generated from the OpenAPI document.
- [PlungeAI in Claude Code](https://www.plungeai.com/docs/integrations/claude-code.md): One `claude mcp add` command, or a project `.mcp.json`. (planned)
- [PlungeAI in Claude.ai and Claude Desktop](https://www.plungeai.com/docs/integrations/claude-ai.md): Skill upload on claude.ai; mcp-remote bridge on Desktop. (planned)
- [PlungeAI in Codex](https://www.plungeai.com/docs/integrations/codex.md): `codex mcp add` with a bearer-token env var. (planned)
- [PlungeAI in Cursor](https://www.plungeai.com/docs/integrations/cursor.md): One-click deeplink or `~/.cursor/mcp.json`. (planned)
- [PlungeAI in VS Code](https://www.plungeai.com/docs/integrations/vscode.md): One-click install or `code --add-mcp`. (planned)
- [PlungeAI in Gemini CLI](https://www.plungeai.com/docs/integrations/gemini-cli.md): `~/.gemini/settings.json` with `httpUrl`. (planned)
- [PlungeAI in OpenCode](https://www.plungeai.com/docs/integrations/opencode.md): `opencode.json` remote MCP entry. (planned)
- [PlungeAI in Windsurf](https://www.plungeai.com/docs/integrations/windsurf.md): `~/.codeium/windsurf/mcp_config.json` snippet. (planned)
- [PlungeAI in Replit](https://www.plungeai.com/docs/integrations/replit.md): One-click install into Replit Agent. (planned)
- [PlungeAI in Lovable](https://www.plungeai.com/docs/integrations/lovable.md): Chat connector or app connector. (planned)
- [PlungeAI in Bolt.new](https://www.plungeai.com/docs/integrations/bolt.md): Custom MCP server in Connectors. (planned)
- [PlungeAI in v0](https://www.plungeai.com/docs/integrations/v0.md): Add MCP in the prompt form; the generated app cannot call MCP. (planned)
- [Any other MCP client](https://www.plungeai.com/docs/integrations/other-mcp-clients.md): URL, header and transport for clients not listed here. (planned)
- [Agentic payments (x402)](https://www.plungeai.com/docs/integrations/agentic-payments.md): Pay x402 services in USDC through the payment agents, with approval. (planned)
- [AWS Marketplace](https://www.plungeai.com/docs/integrations/aws-marketplace.md): Planned: subscribe through AWS Marketplace. (planned)
- [Browser Use](https://www.plungeai.com/docs/integrations/browser-use.md): Planned: private-web data through a browser agent. (planned)
- [Google Cloud Marketplace](https://www.plungeai.com/docs/integrations/google-cloud-marketplace.md): Planned: subscribe through Google Cloud Marketplace. (planned)
- [Google Gemini Enterprise](https://www.plungeai.com/docs/integrations/google-gemini-enterprise.md): Planned: PlungeAI as a grounding source in Gemini Enterprise. (planned)
- [Google Sheets](https://www.plungeai.com/docs/integrations/google-sheets.md): Planned: a sheet function that runs a PlungeAI agent. (planned)
- [LiteLLM](https://www.plungeai.com/docs/integrations/litellm.md): Use the models plane as an OpenAI-wire LiteLLM provider. (planned)
- [n8n](https://www.plungeai.com/docs/integrations/n8n.md): Planned: n8n nodes for agents, tools and workflows. (planned)
- [OpenRouter compatibility](https://www.plungeai.com/docs/integrations/openrouter.md): Endpoint and field parity with OpenRouter, and what you gain. (planned)
- [Render](https://www.plungeai.com/docs/integrations/render.md): Planned: a one-click deploy template for a sample app. (planned)
- [Superhuman](https://www.plungeai.com/docs/integrations/superhuman.md): Planned: PlungeAI skills in Superhuman. (planned)
- [Vercel](https://www.plungeai.com/docs/integrations/vercel.md): Vercel AI SDK against the models plane; v0 over MCP. (planned)
- [Zapier](https://www.plungeai.com/docs/integrations/zapier.md): Planned: a Zapier app for agents and workflows. (planned)
- [Data Integrations](https://www.plungeai.com/docs/data-integrations/overview.md): Planned: run PlungeAI agents over rows in your data tools. (planned)
- [Apache Spark](https://www.plungeai.com/docs/data-integrations/spark.md): Planned: SQL-native UDFs that call agents. (planned)
- [DuckDB](https://www.plungeai.com/docs/data-integrations/duckdb.md): Planned: batch enrichment from DuckDB. (planned)
- [Google BigQuery](https://www.plungeai.com/docs/data-integrations/bigquery.md): Planned: BigQuery remote functions. (planned)
- [Polars](https://www.plungeai.com/docs/data-integrations/polars.md): Planned: a Polars expression plugin. (planned)
- [Snowflake](https://www.plungeai.com/docs/data-integrations/snowflake.md): Planned: a Snowflake UDTF. (planned)
- [Supabase](https://www.plungeai.com/docs/data-integrations/supabase.md): Planned: Supabase Edge Function helpers. (planned)
- [PlungeAI API Glossary](https://www.plungeai.com/docs/resources/glossary.md): Every term used across the API, MCP and skills docs. (planned)
- [Connector catalog](https://www.plungeai.com/docs/resources/connector-catalog.md): OAuth and API-key connectors, BYOK, and how connected accounts reach calls. (planned)
- [Data and privacy](https://www.plungeai.com/docs/resources/data-and-privacy.md): What the models plane stores about a request, how long it keeps it, and which providers process your prompts.
- [Memory](https://www.plungeai.com/docs/resources/memory.md): Long-term memory, and distilling sessions into skills. (planned)
- [Roles and permissions](https://www.plungeai.com/docs/resources/roles-and-permissions.md): Company and team roles, scopes and levels in the Dashboard. (planned)
- [Trust fence and approvals](https://www.plungeai.com/docs/resources/trust-fence.md): Key fences, the trust fence, the agent fence, mission bounds and model guardrails. (planned)
- [API Error Codes and Warnings](https://www.plungeai.com/docs/resources/warnings-and-errors.md): Every error envelope and code, the outcomes, and what to retry. (planned)
- [Webhook setup](https://www.plungeai.com/docs/resources/webhook-setup.md): Planned: signing, retries and verification for outbound webhooks. (planned)
- [Migrate from legacy execute aliases](https://www.plungeai.com/docs/workflows/migration-guide.md): Move `/v1/execute` and `/v1/cnl/*` calls to `/v1/workflows/*`. (planned)
- [Docs for AI agents](https://www.plungeai.com/docs/resources/docs-for-agents.md): Dropped: PlungeAI runs no web crawler, so webmaster guidance does not apply. Replacement: how agents read these docs (`/agents.md`, llms.txt, `.md` twins, Docs MCP).
- [Status](https://www.plungeai.com/docs/resources/status.md): The inference gateway status page, what its readiness check tests, and the health endpoints of the other PlungeAI services.
- [FAQs](https://www.plungeai.com/docs/resources/faqs.md): Answers to common platform, API, billing and security questions. (planned)
- [One API guide](https://www.plungeai.com/docs/one-api.md): The Ocean One API is a single HTTPS front door to the Ocean platform. One base URL, one router, and every capability the platform exposes reachable from it:
- [Quickstart](https://www.plungeai.com/docs/one-api/quickstart.md): Thirty-five calls you can paste into a terminal and run as they are. Every ozk_ sample below is live-verified on the build date (the verifier runs the ones marked in the source; the create/run/delete ones mutate state and are run by hand). Two minutes of setup:
- [Authentication & keys](https://www.plungeai.com/docs/one-api/authentication.md): Every route except GET /health and GET /v1/openapi.json needs a key. One ozk_ platform key opens every plane on https://api.plungeai.com (models, tools, agents, workflows, MCP, discovery, traces and the connector proxy) and the MCP server on https://mcp.plungeai.com. Two older prefixes, …
- [Models plane](https://www.plungeai.com/docs/one-api/models.md): The models plane is the OpenAI-compatible surface: POST /v1/chat/completions, POST /v1/embeddings, GET /v1/models. Base URL https://api.plungeai.com. Auth is your ozk_… account key in Authorization: Bearer (only: X-API-Key is a 401 on this plane, except on /v1/messages, 3.16), billed to your …
- [Streaming](https://www.plungeai.com/docs/one-api/streaming.md): Three surfaces stream over Server-Sent Events (SSE): the models plane (/v1/chat/completions with stream:true), the workflows plane (/v1/workflows/execute-stream), and the agents plane (/v1/agents/:id/execute with stream:true). The models plane speaks the OpenAI delta wire; the workflows plane …
- [OpenRouter compatibility](https://www.plungeai.com/docs/one-api/openrouter-compat.md): Point your OpenAI or OpenRouter client at https://api.plungeai.com/v1, swap the key for your ozk_… platform key, and POST /v1/chat/completions works with the same provider/model slugs and the same models[] fallback array — Ocean is an OpenAI-compatible router with OpenRouter-style …
- [Tools plane](https://www.plungeai.com/docs/one-api/tools.md): A tool agent is any active registry agent with a typed invocation contract. The tools plane is the shortest path from "I want Brave search" to a result: three routes, one security check, one execution path. Every call becomes a one-task workflow on the engine, so it lands in your execution …
- [Connectors & connected accounts](https://www.plungeai.com/docs/one-api/connectors.md): A connector is a third-party integration a user connects once — Gmail, Microsoft 365, GitHub, Adobe, Slack, Stripe, Notion, … A connected account is that user's live credential row. Tool agents then act *as that user*: google-gmail reads the mailbox of whoever owns the ozk_ key that made the …
- [Discovery](https://www.plungeai.com/docs/one-api/discovery.md): Discovery is the read-only catalog behind every other plane: agents, skills, plugins, MCP servers, connectors, models, providers and (once you have saved some) workflows. Four routes, all ozk_-authenticated, all backed by the registry service (orchestration/api-gateway/routes/discovery.ts → …
- [Agents plane](https://www.plungeai.com/docs/one-api/agents.md): The agents plane runs one registry agent per request and hands back its result. It is the execution plane you reach with an ozk_ key (see Authentication) at POST /v1/agents/:id/execute. Every call wraps exactly one minimal CNL task in the engine envelope, so the agents plane is the single-task …
- [Workflows plane](https://www.plungeai.com/docs/one-api/workflows.md): The workflows plane runs a CNL workflow — one or many agent tasks orchestrated by the engine — and hands back a pointer to the result. Reach it with an ozk_ key (Authentication) at POST /v1/workflows/execute (inline) or POST /v1/workflows/:id/execute (saved). Base URL is always …
- [MCP plane](https://www.plungeai.com/docs/one-api/mcp.md): The MCP plane is bidirectional: inbound, the platform *is* an MCP server you point a client at; outbound, you connect the platform to *other* MCP servers and call their tools during a run. Both use an ozk_ key (Authentication). Base URL is https://api.plungeai.com. Source: …
- [Traces & observability](https://www.plungeai.com/docs/one-api/traces-observability.md): Every One API response is traceable. This chapter covers the trace id, the GET /v1/traces/:id read, execution history and cost, the response headers, and what is not observable through the API today. Base URL is https://api.plungeai.com; reads use an ozk_ key (Authentication). Source: …
- [Errors, limits & headers](https://www.plungeai.com/docs/one-api/errors-limits.md): The platform has two error envelopes. The execution planes (tools, agents, workflows, MCP, discovery, traces) use the router envelope; the models plane (/v1/chat/completions, /v1/embeddings, /v1/models) uses the OpenAI-shaped envelope from the inference gateway. Branch on the HTTP status and, …
- [Skills, plugins & capability injection](https://www.plungeai.com/docs/one-api/skills-plugins-capabilities.md): The platform does not ship one agent per behaviour. It ships one agent — one-agent, whose loop mode runs the mission (see Agents plane) — into which capabilities are injected per run. *Capability injection* is the six kinds below: skills, experts, persona, backgrounds, plugins, and MCP servers. …
- [SDKs & clients](https://www.plungeai.com/docs/one-api/sdks-and-clients.md): You do not need an Ocean-specific SDK to use the One API. The models plane is OpenAI-wire, so every OpenAI-compatible client works with a base-URL swap; the execution planes are plain HTTP+JSON and have official SDKs in TypeScript, Python, Go and Rust. This chapter lists the options, shortest …
- [Bots](https://www.plungeai.com/docs/one-api/bots.md): A bot is a saved workflow (kind: bot) that runs on a clock, answers messages, keeps its own memory and files, and stays inside a policy you set. This chapter is the REST surface for all of it: save a bot, set what it may do and spend, watch and answer its runs, schedule it, start it from …
- [Companies](https://www.plungeai.com/docs/one-api/companies.md): A company is a campus. You describe it in YAML documents, save them like any workflow, and apply them. The platform compiles them into a plan and runs it: it puts items (a feature, a brief, a piece of content) through each building's offices in order, and it stops at gates where a person …
- [MCP guide](https://www.plungeai.com/docs/mcp.md): The PlungeAI MCP server puts the PlungeAI platform behind the Model Context Protocol. You connect an MCP client (Claude Code, Cursor, VS Code, Codex, Lovable, Replit, …) once, then ask for things in plain language. The client picks one of the server's 20 plungeai_* tools, fills in the …
- [Quickstart](https://www.plungeai.com/docs/mcp/quickstart.md): Five minutes from nothing to a real run. The endpoint is https://mcp.plungeai.com/v1; https://api.plungeai.com/v1/mcp is the same server if you prefer the One API host (0.2).
- [Authentication & keys](https://www.plungeai.com/docs/mcp/authentication.md): Every MCP call needs an ozk_ key. The key is your identity: it resolves to one user account, and every tool reads and writes only what that account owns. There is no OAuth sign-in on the MCP server today; bearer keys are the only way in. This chapter uses https://mcp.plungeai.com/v1; …
- [Connecting clients](https://www.plungeai.com/docs/mcp/connecting-clients.md): Every client needs the same two things: the URL https://mcp.plungeai.com/v1 and the header Authorization: Bearer ozk_YOUR_KEY. What differs is where each client keeps its config and what it calls the fields. https://api.plungeai.com/v1/mcp is the same server and works in any of these configs; …
- [Protocol & transport](https://www.plungeai.com/docs/mcp/protocol.md): tools.ts, tool-exec.ts, extras.ts, orchestration/api-gateway/routes/mcp.ts, orchestration/api-gateway/lib/auth.ts, and the MCP TypeScript SDK 1.29.0 (node_modules/@modelcontextprotocol/sdk: server/index.js, server/mcp.js, server/webStandardStreamableHttp.js, shared/protocol.js, types.js).
- [Discovery](https://www.plungeai.com/docs/mcp/discovery.md): Before you run anything, find it. Discovery is three steps. Each one is a read-only tool call that costs no credits:
- [Tools](https://www.plungeai.com/docs/mcp/tools.md): A structured tool-agent is a registry agent whose card has a Parameters table: weather-agent, markitdown, google-gmail, resend, x402-wallet-agent, … It takes typed fields, not a sentence. plungeai_execute_tool runs one operation of one such agent. It uses the same engine pipeline as every other …
- [Agents & missions](https://www.plungeai.com/docs/mcp/agents-missions.md): Two tools run "one thing" without a workflow. plungeai_execute_agent runs one prompt-driven agent once, and you choose the model. plungeai_run_mission runs a bounded autonomous mission: a tool loop with a goal, a tool fence, an iteration cap and long-term memory. Structured tool-agents that …
- [Workflows](https://www.plungeai.com/docs/mcp/workflows.md): Your workflows are saved CNL workflows. CNL is the platform's YAML workflow language. Users call their workflows "my agents", and most day-to-day work is here: find a workflow, run it, inspect it. There is no separate "MCP workspace". A workflow you create or run here is the same workflow you …
- [Runs, results & follow-ups](https://www.plungeai.com/docs/mcp/runs-results.md): Every execution tool (plungeai_execute_workflow, plungeai_execute_agent, plungeai_execute_tool, plungeai_run_mission, plungeai_learn) creates an execution and answers with its execution id. This chapter covers what you do with that id afterwards: read the output, check the status, browse your …
- [Chat, memory & skills](https://www.plungeai.com/docs/mcp/chat-memory-skills.md): Three tools keep something for you across calls: a conversation, a memory, a skill. The examples use https://mcp.plungeai.com/v1. https://api.plungeai.com/v1/mcp is the same server.
- [Scheduling](https://www.plungeai.com/docs/mcp/scheduling.md): plungeai_schedule creates and manages cron jobs on the platform scheduler. A job belongs to the user behind your key, and every run of a workflow, agent, query or mission_ref job lands in your normal execution history (heartbeats are the exception, 11.3), where you read it like any other result …
- [Prompts & resources](https://www.plungeai.com/docs/mcp/prompts-resources.md): orchestration/mcp-gateway/server.ts (resource templates, handler wiring), orchestration/mcp-gateway/skill-dist.generated.ts, orchestration/mcp-gateway/llms-routes.ts, MCP SDK 1.29.0 (types.js McpError, shared/protocol.js).
- [Errors, feedback & limits](https://www.plungeai.com/docs/mcp/errors-limits.md): prompts.ts, tools.ts, tool-exec.ts, extras.ts, activity-log.ts, log-view.ts, execution-do.ts, leg-state.ts, core/core-base/content-guard.ts, orchestration/api-gateway/lib/auth.ts, MCP SDK 1.29.0, live registry cards (2026-09-24).
- [Tool reference](https://www.plungeai.com/docs/mcp/tool-reference.md): Every tool the server exposes, in the order tools/list returns them. You rarely call these by name: your client reads the list when it connects and picks the tool from your request. This chapter is the exact contract behind that choice. The server is https://mcp.plungeai.com/v1; …
- [Troubleshooting & gotchas](https://www.plungeai.com/docs/mcp/troubleshooting.md): extras.ts, activity-log.ts, core/core-base/provider-ids.ts, core/agent-core/index.ts, agents/agents/one-agent/call-config.ts, orchestration/api-gateway/routes/mcp.ts, live registry and registry cards (2026-09-24), live /health, /v1/info, 401/405/413 responses (2026-09-24).
- [Companies](https://www.plungeai.com/docs/mcp/companies.md): A company is a campus compiled from documents you saved as workflows: one kind: campus document, its kind: building documents and their offices. plungeai_companies is the MCP door to it, action for action the One API's /v1/companies: the same company-service, called as you, with the same bodies …
- [Connections](https://www.plungeai.com/docs/mcp/connections.md): plungeai_connections manages the accounts your agents act through, action for action the One API's /v1/connections. Credentials are stored encrypted on the compliance database and never come back out: a list shows provider, method, status and when, nothing else. Full parameter table: 14.22.
- [OceanCode guide](https://www.plungeai.com/docs/oceancode.md): oceancode is one binary and one process. This page builds it, shows the two ways to start it, and lists where it keeps its files.
- [Configuration](https://www.plungeai.com/docs/oceancode/configuration.md): oceancode reads a JSON config file and a set of environment variables. Nothing needs to be configured to start — every key falls back to a built-in default.
- [Plan mode and todos](https://www.plungeai.com/docs/oceancode/plan-mode-and-todos.md): Two separate things share the word "plan": the step list the model keeps as it works, and plan mode, an agent that researches and writes a plan file before anything is changed.
- [Session ledger and export](https://www.plungeai.com/docs/oceancode/session-ledger-and-export.md): A long session would grow to a huge, ever-slower context. oceancode avoids that with the session ledger: the model sees a small, fixed window of recent turns, and everything older is kept verbatim in Markdown files beside the session — never summarized away.
- [Headless and server](https://www.plungeai.com/docs/oceancode/headless-and-server.md): oceancode runs without a UI two ways: a one-shot run for scripts and CI, and a long-lived serve that exposes the engine's HTTP surface to clients. The terminal UI is Ocean pager, which embeds the engine in its own process (see 19 · Ocean pager); serve is the headless surface.
- [Bounding a long run](https://www.plungeai.com/docs/oceancode/bounding-a-long-run.md): A run is bounded by the money and time you set, not by an arbitrary step count. Set nothing and a run keeps going until the work is done (or the no-progress guard stops it, below).
- [Capabilities and plugins](https://www.plungeai.com/docs/oceancode/capabilities.md): Skills, sub-agents, personas, commands and MCP servers are all capabilities, and oceancode finds them the same way: one discovery walk over five tiers, across four ecosystems, with a single rule for names that collide and a separate rule for what a capability is allowed to do.
- [Hooks](https://www.plungeai.com/docs/oceancode/hooks.md): A hook runs your own command (or an HTTP endpoint) at a fixed point in a run and hands back a typed decision the engine acts on. Hooks are configured in a Claude Code settings.json / hooks.json shape, so a hook you already wrote for Claude Code runs here unchanged.
- [MCP servers](https://www.plungeai.com/docs/oceancode/mcp.md): An MCP server is an external process (or HTTP endpoint) that contributes tools, resources and prompts to a run. oceancode reads the same server-config files the other tools use, so a server you configured for Claude Code, Cursor or OpenCode is picked up as-is.
- [Permissions and sandbox](https://www.plungeai.com/docs/oceancode/permissions-and-sandbox.md): OceanCode decides what a tool may do in three layers, from softest to hardest:
- [Jev decisions](https://www.plungeai.com/docs/oceancode/jev-decisions.md): OceanCode can put small typed questions to TypeSafe Jev (System One, pinned model jev-1.13.0) at ten decision points — "would this command delete data?", "which block of this output answers the step?" — and use the answers as advice. Jev answers with probabilities: a noul (the probability of …
- [15 · Platform mode (PlungeAI connectivity)](https://www.plungeai.com/docs/oceancode/platform-mode.md): oceancode ships in two builds. The default build is the standalone coding agent and contains no platform code at all. The platform build is produced with
- [16 · Testing and gates](https://www.plungeai.com/docs/oceancode/testing-and-gates.md): Everything in oceancode is verified by one script — ./check.sh — and a handful of opt-in lanes on it. This page covers what those lanes are, and then the one test surface a terminal UI needs that unit tests cannot give it: the interface probe, which drives the real TUI over a pseudo-terminal …
- [Distribution and updates](https://www.plungeai.com/docs/oceancode/distribution.md): oceancode ships as two self-contained binaries: the engine oceancode and the terminal UI ocean-pager it launches, installed side by side. This page covers installing it, keeping it current, verifying a download, and removing it. Every download is checksummed, and every install channel agrees on …
- [18 · Operations](https://www.plungeai.com/docs/oceancode/operations.md): Running oceancode for a long time — days, not minutes — is a first-class case. This page covers the operational surface that keeps a long run healthy: a metrics scrape, database and ledger retention, the storage doctor, crash recovery, the event-bus drop counter, and log levels. Everything here …
- [Ocean pager — the terminal UI](https://www.plungeai.com/docs/oceancode/pager.md): Ocean pager is oceancode's terminal UI. A plain oceancode execs Ocean pager (ocean-pager); the pager and the Ocean engine run in one process over typed ACP channels — no HTTP between UI and engine. --db, --directory, --listen and --verbose are passed through.
- [Xcode and other ACP editors — oceancode acp](https://www.plungeai.com/docs/oceancode/xcode.md): oceancode acp runs the Ocean engine as an Agent Client Protocol (ACP) agent on the process's stdin/stdout. An ACP editor — Xcode 26.6 and later, Zed, JetBrains, Neovim — starts the binary itself as a subprocess and talks newline-delimited JSON-RPC over the pipe. There is no URL, no port and no …
- [CLI reference](https://www.plungeai.com/docs/oceancode/cli-reference.md): oceancode is one binary: oceancode [subcommand] [flags] [args]. With no subcommand it starts Ocean pager. acp runs it as an editor agent, and serve, run, goal and workflow run it headless. 01 · Getting started explains the three boot shapes. This page lists every subcommand, its flags and its …
- [Ocean pager reference](https://www.plungeai.com/docs/oceancode/pager-reference.md): This page lists Ocean pager's slash commands, keyboard shortcuts, mode ring, config.toml settings, themes and notification options. For how the pager starts, its environment variables and what is wired to the Ocean engine, see Ocean pager.
- [Work modes](https://www.plungeai.com/docs/oceancode/work-modes.md): A work mode decides how agents work together on your prompt. There are three answers to "who decides?":
- [HTTP API reference](https://www.plungeai.com/docs/oceancode/http-api.md): oceancode serve runs the engine as a long-lived HTTP server, by default on http://127.0.0.1:4096 (--port and --host change it; the default pager shape takes --listen <host:port>). Every route below is relative to that base URL. HTTP basic auth is off until OC_SERVER_PASSWORD is set; then it …
- [Create chat completion](https://www.plungeai.com/docs/api-reference/models/create-chat-completion.md): Send messages to a model and get a completion, or stream it as SSE chunks. Ordered fallback with `models[]`, `sort`, presets and an opt-in response cache.
- [Create message (Anthropic)](https://www.plungeai.com/docs/api-reference/models/create-message.md): The Anthropic Messages API on the models plane: point an Anthropic SDK at `https://api.plungeai.com` with your `ozk_` key in `x-api-key`. Any model; `anthropic/*` gets your body as sent, every other model a translation.
- [Create embeddings](https://www.plungeai.com/docs/api-reference/models/create-embeddings.md): Turn a string or a list of strings into embedding vectors (OpenAI-compatible).
- [List models](https://www.plungeai.com/docs/api-reference/models/list-models.md): The priced model catalog routing candidates are drawn from. `pricing.in` and `pricing.out` are the provider cost basis in USD per 1M tokens, before your org markup.
- [Price list](https://www.plungeai.com/docs/api-reference/models/pricing.md): The public price list: no key.
- [Get generation](https://www.plungeai.com/docs/api-reference/models/get-generation.md): Post-hoc usage and cost of one completion. id = the gen-… completion id (/api/v1) or the x-request-id.
- [Get credits](https://www.plungeai.com/docs/api-reference/models/get-credits.md): Lifetime credits bought and used by the calling account, in USD.
- [Get current key](https://www.plungeai.com/docs/api-reference/models/get-key.md): The calling key: label, monthly limit, usage this month, rate limit. Also served at /v1/auth/key.
- [List model endpoints](https://www.plungeai.com/docs/api-reference/models/list-model-endpoints.md): The endpoint that serves one model, with per-token pricing (Ocean has one upstream per model).
- [Create completion](https://www.plungeai.com/docs/api-reference/models/create-completion.md): Legacy text completion (proxied to inference-gateway): a chat completion with one user message, answered as text_completion.
- [Create chat completion (/api/v1)](https://www.plungeai.com/docs/api-reference/models/openrouter-create-chat-completion.md): Chat completion on the OpenRouter-compatible /api/v1 base. The same engine as POST /v1/chat/completions, with OpenRouter’s error envelope.
- [Create message (/api/v1)](https://www.plungeai.com/docs/api-reference/models/openrouter-create-message.md): The Anthropic Messages API on the OpenRouter-compatible /api/v1 base. The same handler as POST /v1/messages, Anthropic’s error envelope included; `fallbacks` takes up to 3 models.
- [Create embeddings (/api/v1)](https://www.plungeai.com/docs/api-reference/models/openrouter-create-embeddings.md): Embeddings on the OpenRouter-compatible /api/v1 base.
- [Create completion (/api/v1)](https://www.plungeai.com/docs/api-reference/models/openrouter-create-completion.md): Legacy text completion on the OpenRouter-compatible /api/v1 base.
- [List models (/api/v1)](https://www.plungeai.com/docs/api-reference/models/openrouter-list-models.md): The model catalog on the OpenRouter-compatible /api/v1 base. Needs no key.
- [Get generation (/api/v1)](https://www.plungeai.com/docs/api-reference/models/openrouter-get-generation.md): Usage and cost of one completion: id is the gen-… completion id.
- [Get credits (/api/v1)](https://www.plungeai.com/docs/api-reference/models/openrouter-get-credits.md): Lifetime credits bought and used by the calling account, in USD.
- [Get current key (/api/v1)](https://www.plungeai.com/docs/api-reference/models/openrouter-get-key.md): The calling key: label, monthly limit, usage this month, rate limit.
- [List model endpoints (/api/v1)](https://www.plungeai.com/docs/api-reference/models/openrouter-list-model-endpoints.md): The endpoint that serves one model, with per-token pricing.
- [Search the registry](https://www.plungeai.com/docs/api-reference/discovery/search-registry.md): Hybrid semantic and keyword search over capability cards. Pages with `limit` and `offset`; a page shorter than `limit` is the last one.
- [Recommend a card](https://www.plungeai.com/docs/api-reference/discovery/recommend-card.md): Get the one best capability card for a task, with a score.
- [Get a card](https://www.plungeai.com/docs/api-reference/discovery/get-card.md): Read one capability card as markdown (the LLM view): operations, examples and "Not for" redirects.
- [Resolve a task](https://www.plungeai.com/docs/api-reference/discovery/resolve-task.md): Resolve a task to one tool, its operation and an example call, with a calibrated confidence.
- [List tools](https://www.plungeai.com/docs/api-reference/tools/list-tools.md): List the active tool agents, 50 per page by default (at most 100).
- [Get a tool contract](https://www.plungeai.com/docs/api-reference/tools/get-tool-contract.md): The invocation contract of one tool agent: JSON Schema parameters, operations, approval gates and examples.
- [Execute a tool](https://www.plungeai.com/docs/api-reference/tools/execute-tool.md): Run one operation of a tool agent with typed params. Gated and money verbs refuse unattended calls.
- [List agents](https://www.plungeai.com/docs/api-reference/agents/list-agents.md): List the active agents, 50 per page by default (at most 100).
- [List agent categories](https://www.plungeai.com/docs/api-reference/agents/list-agent-categories.md): Agent categories with the number of active agents in each.
- [Execute an agent](https://www.plungeai.com/docs/api-reference/agents/execute-agent.md): Run one agent with a prompt. Sync by default; `sync: false` returns a pointer to redeem later; `stream: true` streams OpenAI-shaped chunks.
- [Get an agent result](https://www.plungeai.com/docs/api-reference/agents/get-agent-result.md): Redeem the result of an async agent run with the `workflow_id` and `task_id` it returned.
- [Execute an inline workflow](https://www.plungeai.com/docs/api-reference/workflows/execute-inline-workflow.md): Run a CNL workflow sent in the body, as JSON `{workflow, input}` or as a raw `text/yaml` document. Returns a pointer; read the content from the result route.
- [Stream an inline workflow](https://www.plungeai.com/docs/api-reference/workflows/stream-inline-workflow.md): Run an inline workflow and stream every engine event as SSE until `workflow_completed` or `workflow_error`.
- [Execute a saved workflow](https://www.plungeai.com/docs/api-reference/workflows/execute-saved-workflow.md): Run one of your saved workflows by id with an optional `input` or `inputs`.
- [Stream a saved workflow](https://www.plungeai.com/docs/api-reference/workflows/stream-saved-workflow.md): Run a saved workflow and stream its engine events as SSE.
- [Get a workflow result](https://www.plungeai.com/docs/api-reference/workflows/get-workflow-result.md): Read the stored output of one task of a run, usually the `final_task_id` the execute call returned.
- [Cancel an execution](https://www.plungeai.com/docs/api-reference/workflows/cancel-execution.md): Ask a running execution of yours to stop. Cancellation is cooperative.
- [List workflows](https://www.plungeai.com/docs/api-reference/workflows/list-workflows.md): List your saved workflows, agents, bots and campaigns.
- [Create a workflow](https://www.plungeai.com/docs/api-reference/workflows/create-workflow.md): Save a workflow, agent, bot or campaign.
- [Get a workflow](https://www.plungeai.com/docs/api-reference/workflows/get-workflow.md): Read one saved workflow with its YAML.
- [Update a workflow](https://www.plungeai.com/docs/api-reference/workflows/update-workflow.md): Change a workflow: name, description, YAML, kind or folder.
- [Delete a workflow](https://www.plungeai.com/docs/api-reference/workflows/delete-workflow.md): Delete a workflow.
- [List versions](https://www.plungeai.com/docs/api-reference/workflows/list-workflow-versions.md): List the saved versions of a workflow, newest first.
- [Save a version](https://www.plungeai.com/docs/api-reference/workflows/save-workflow-version.md): Save the current YAML as a new version.
- [Restore a version](https://www.plungeai.com/docs/api-reference/workflows/restore-workflow-version.md): Make a saved version the live YAML again.
- [List executions](https://www.plungeai.com/docs/api-reference/executions/list-executions.md): List your executions, newest first.
- [Get an execution](https://www.plungeai.com/docs/api-reference/executions/get-execution.md): Status of an execution (poll this).
- [Delete an execution](https://www.plungeai.com/docs/api-reference/executions/delete-execution.md): Delete an execution and its stored result.
- [Get the output](https://www.plungeai.com/docs/api-reference/executions/get-execution-output.md): The run’s final output (json, yaml, markdown or text).
- [Get the conversation](https://www.plungeai.com/docs/api-reference/executions/get-execution-conversation.md): The follow-up and continue turns of a run.
- [List the files](https://www.plungeai.com/docs/api-reference/executions/list-execution-files.md): Files the run produced.
- [Continue or approve](https://www.plungeai.com/docs/api-reference/executions/continue-execution.md): Answer a paused run’s question or approve its held action.
- [Follow up](https://www.plungeai.com/docs/api-reference/executions/followup-execution.md): Message a run: queued while it runs, a new turn once it finished.
- [Steer a run](https://www.plungeai.com/docs/api-reference/executions/steer-execution.md): Queue a message for a running execution.
- [Cancel an execution](https://www.plungeai.com/docs/api-reference/executions/cancel-execution.md): Cancel a running execution (cooperative).
- [Stream an execution](https://www.plungeai.com/docs/api-reference/executions/stream-execution.md): Re-attach to a running execution (SSE).
- [Get permissions](https://www.plungeai.com/docs/api-reference/bots/get-bot-permissions.md): A bot’s permission presets, admin locks and spend caps.
- [Set permissions](https://www.plungeai.com/docs/api-reference/bots/set-bot-permissions.md): Set a bot’s permission presets, locks and spend caps.
- [List workspace files](https://www.plungeai.com/docs/api-reference/bots/list-workspace-files.md): A bot’s persistent workspace files.
- [Download a workspace file](https://www.plungeai.com/docs/api-reference/bots/download-workspace-file.md): Download one workspace file.
- [Read the inbox](https://www.plungeai.com/docs/api-reference/bots/get-bot-inbox.md): A bot’s inbox.
- [List bindings](https://www.plungeai.com/docs/api-reference/bots/list-bindings.md): Chats bound to a bot.
- [Bind a chat](https://www.plungeai.com/docs/api-reference/bots/bind-chat.md): Bind a paired chat to a bot.
- [Unbind a chat](https://www.plungeai.com/docs/api-reference/bots/unbind-chat.md): Unbind a chat from a bot.
- [List bot groups](https://www.plungeai.com/docs/api-reference/bots/list-bot-groups.md): Your bot groups.
- [Create a bot group](https://www.plungeai.com/docs/api-reference/bots/create-bot-group.md): Create a bot group.
- [Replace a bot group](https://www.plungeai.com/docs/api-reference/bots/replace-bot-group.md): Replace a bot group.
- [Delete a bot group](https://www.plungeai.com/docs/api-reference/bots/delete-bot-group.md): Delete a bot group.
- [Read a group thread](https://www.plungeai.com/docs/api-reference/bots/get-bot-group-thread.md): A bot group’s shared thread.
- [List paired channels](https://www.plungeai.com/docs/api-reference/bots/list-channels.md): Your paired channels.
- [Mint a pairing code](https://www.plungeai.com/docs/api-reference/bots/create-pairing-code.md): Mint a pairing code.
- [List schedules](https://www.plungeai.com/docs/api-reference/schedules/list-schedules.md): List your schedules.
- [Create a schedule](https://www.plungeai.com/docs/api-reference/schedules/create-schedule.md): Create a schedule of a saved workflow (cron, or one-time with run_at).
- [Get a schedule](https://www.plungeai.com/docs/api-reference/schedules/get-schedule.md): Get a schedule with its latest runs.
- [Update a schedule](https://www.plungeai.com/docs/api-reference/schedules/update-schedule.md): Change a schedule.
- [Delete a schedule](https://www.plungeai.com/docs/api-reference/schedules/delete-schedule.md): Delete a schedule.
- [Run now](https://www.plungeai.com/docs/api-reference/schedules/run-schedule.md): Run a schedule now.
- [Pause a schedule](https://www.plungeai.com/docs/api-reference/schedules/pause-schedule.md): Pause a schedule.
- [Resume a schedule](https://www.plungeai.com/docs/api-reference/schedules/resume-schedule.md): Resume a paused schedule.
- [Wake a schedule](https://www.plungeai.com/docs/api-reference/schedules/wake-schedule.md): Wake the schedule’s workflow once.
- [List runs](https://www.plungeai.com/docs/api-reference/schedules/list-schedule-runs.md): List a schedule’s runs.
- [List webhook triggers](https://www.plungeai.com/docs/api-reference/triggers/list-webhook-triggers.md): List a schedule's webhook triggers.
- [Mint a webhook trigger](https://www.plungeai.com/docs/api-reference/triggers/create-webhook-trigger.md): Mint a webhook trigger on a schedule.
- [Revoke a webhook trigger](https://www.plungeai.com/docs/api-reference/triggers/delete-webhook-trigger.md): Revoke a webhook trigger.
- [Rotate a webhook trigger](https://www.plungeai.com/docs/api-reference/triggers/rotate-webhook-trigger.md): Rotate a webhook trigger.
- [List email triggers](https://www.plungeai.com/docs/api-reference/triggers/list-email-triggers.md): List a schedule's email triggers.
- [Mint an email trigger](https://www.plungeai.com/docs/api-reference/triggers/create-email-trigger.md): Mint an email trigger on a schedule.
- [Revoke an email trigger](https://www.plungeai.com/docs/api-reference/triggers/delete-email-trigger.md): Revoke an email trigger.
- [Rotate an email trigger](https://www.plungeai.com/docs/api-reference/triggers/rotate-email-trigger.md): Rotate an email trigger.
- [List outbound hooks](https://www.plungeai.com/docs/api-reference/triggers/list-hooks.md): List a schedule's outbound hooks.
- [Mint an outbound hook](https://www.plungeai.com/docs/api-reference/triggers/create-hook.md): Mint an outbound hook on a schedule.
- [Revoke an outbound hook](https://www.plungeai.com/docs/api-reference/triggers/delete-hook.md): Revoke an outbound hook.
- [Recall memory](https://www.plungeai.com/docs/api-reference/memory/recall-memory.md): Recall your long-term memory entries (optionally filtered by text).
- [Remember a fact](https://www.plungeai.com/docs/api-reference/memory/remember.md): Remember a fact.
- [Forget](https://www.plungeai.com/docs/api-reference/memory/forget.md): Forget one entry by id, or purge every entry containing some text.
- [Search past runs](https://www.plungeai.com/docs/api-reference/memory/search-runs.md): Search your past runs.
- [Get a past run](https://www.plungeai.com/docs/api-reference/memory/get-run.md): One past run’s stored result.
- [List skills](https://www.plungeai.com/docs/api-reference/skills/list-skills.md): List your learned skills.
- [Save a skill](https://www.plungeai.com/docs/api-reference/skills/learn-skill.md): Save a skill.
- [Delete a skill](https://www.plungeai.com/docs/api-reference/skills/delete-skill.md): Delete one of your skills.
- [List templates](https://www.plungeai.com/docs/api-reference/templates/list-templates.md): Browse the workflow, agent and bot templates.
- [Get a template](https://www.plungeai.com/docs/api-reference/templates/get-template.md): One template and its YAML.
- [Use a template](https://www.plungeai.com/docs/api-reference/templates/use-template.md): Copy a template into your account as a new workflow.
- [List connections](https://www.plungeai.com/docs/api-reference/connections/list-connections.md): List your connections, or one customer’s (status only).
- [Connect a provider](https://www.plungeai.com/docs/api-reference/connections/connect-provider.md): Bring a key for a provider (yours, or your customer’s).
- [Disconnect a provider](https://www.plungeai.com/docs/api-reference/connections/disconnect-provider.md): Disconnect a provider (yours, or your customer’s).
- [Mint a connect link](https://www.plungeai.com/docs/api-reference/connections/create-connect-link.md): Get a hosted connect link to send to your customer.
- [List companies](https://www.plungeai.com/docs/api-reference/companies/list-companies.md): Your applied campuses: mode, status, building count and the approvals waiting at each door.
- [Apply a company](https://www.plungeai.com/docs/api-reference/companies/apply-company.md): Compile the saved campus, building and office documents into the stored plan; inline offices are saved as workflows.
- [Get the layout](https://www.plungeai.com/docs/api-reference/companies/get-company-layout.md): The compiled company: buildings with policy, floors, intake and pipeline, and their offices.
- [Get the snapshot](https://www.plungeai.com/docs/api-reference/companies/get-company-snapshot.md): The company now: office states, active items, the line at the door, spend today and items shipped in 7 days.
- [List events](https://www.plungeai.com/docs/api-reference/companies/list-company-events.md): The event log as a JSON page after a seq, or a live SSE feed.
- [Report events](https://www.plungeai.com/docs/api-reference/companies/report-company-events.md): A local building’s node mirrors its own events up with the owner’s key.
- [Get a building slice](https://www.plungeai.com/docs/api-reference/companies/get-building-slice.md): What a local building’s node pulls to run it: pipeline, policy, project and office ids.
- [Create an item](https://www.plungeai.com/docs/api-reference/companies/create-company-item.md): Put an item into a building at its intake.
- [Read an item](https://www.plungeai.com/docs/api-reference/companies/get-company-item.md): One item in full: its bodies and every run, approval and own event. The snapshot carries only the lean row.
- [Pause an item](https://www.plungeai.com/docs/api-reference/companies/pause-company-item.md): The item keeps its step and is not walked until it is resumed.
- [Resume an item](https://www.plungeai.com/docs/api-reference/companies/resume-company-item.md): Resume a paused or parked item at the step it stopped on.
- [Retry an item](https://www.plungeai.com/docs/api-reference/companies/retry-company-item.md): Start the item’s step again as the next attempt, or at the pipeline’s retry target.
- [Cancel an item](https://www.plungeai.com/docs/api-reference/companies/cancel-company-item.md): End the item failed with parked_reason cancelled.
- [Steer an item](https://www.plungeai.com/docs/api-reference/companies/steer-company-item.md): A note the next office run receives once, appended to its input.
- [List approvals](https://www.plungeai.com/docs/api-reference/companies/list-company-approvals.md): The gates waiting on a person and the tool permissions office runs asked for.
- [Decide an approval](https://www.plungeai.com/docs/api-reference/companies/decide-company-approval.md): Approve or reject a pending gate or tool permission.
- [Set the mode](https://www.plungeai.com/docs/api-reference/companies/set-company-mode.md): Switch the company live between supervised, tiered and autonomous.
- [Start the clock](https://www.plungeai.com/docs/api-reference/companies/start-company.md): Arm the campus clock: its items are walked until it is stopped.
- [Stop the clock](https://www.plungeai.com/docs/api-reference/companies/stop-company.md): Disarm the campus clock; items keep their step and wait.
- [Delete a company](https://www.plungeai.com/docs/api-reference/companies/delete-company.md): Delete a stopped or never-started company and every row of it.
- [Agent Call](https://www.plungeai.com/docs/api-reference/agent-call/agent-call.md): Agent Call — a bare building block, a workflow, or a saved agent (agent: <id>[@n]) in one body.
- [List MCP tools](https://www.plungeai.com/docs/api-reference/mcp/list-mcp-tools.md): The MCP server tool list as a plain GET; the answer is the JSON-RPC `tools/list` envelope with the tools under `result.tools`.
- [MCP endpoint (JSON-RPC)](https://www.plungeai.com/docs/api-reference/mcp/mcp-endpoint.md): The Streamable HTTP MCP endpoint: `initialize`, then `tools/list` and `tools/call`. The samples use the MCP host `https://mcp.plungeai.com/v1`, the same server.
- [Open an MCP run](https://www.plungeai.com/docs/api-reference/mcp/create-mcp-run.md): Connect catalog MCP servers for a run and get their namespaced tool table. Always close the run when done.
- [List MCP run tools](https://www.plungeai.com/docs/api-reference/mcp/list-mcp-run-tools.md): List the namespaced tools (`mcp__<server>__<tool>`) of an open MCP run.
- [Call an MCP run tool](https://www.plungeai.com/docs/api-reference/mcp/call-mcp-run-tool.md): Call one namespaced tool of an open MCP run with its arguments.
- [Close an MCP run](https://www.plungeai.com/docs/api-reference/mcp/close-mcp-run.md): Close an MCP run and drop its state. Idempotent.
- [Get a trace](https://www.plungeai.com/docs/api-reference/traces/get-trace.md): The persisted trace of one run: execution spans and the gateway request log for the trace id.
- [Health](https://www.plungeai.com/docs/api-reference/meta/health.md): Liveness probe of the One API router. No key needed.
- [OpenAPI spec](https://www.plungeai.com/docs/api-reference/meta/get-openapi-spec.md): The OpenAPI 3.1 document of the One API. The docs copy with tags is at [/openapi.json](/openapi.json).
- [llms.txt](https://www.plungeai.com/docs/api-reference/meta/llms-txt.md): The One API guide index for AI coding agents, as plain text (llmstxt.org).
- [llms-full.txt](https://www.plungeai.com/docs/api-reference/meta/llms-full-txt.md): The whole One API Developer Guide 3.1 and the external API reference in one markdown file.
- [Guide (HTML)](https://www.plungeai.com/docs/api-reference/meta/docs.md): The old address of the One API Developer Guide on the API host; it answers 301 to the guide's pages on www.plungeai.com.
- [Who am I](https://www.plungeai.com/docs/api-reference/meta/get-whoami.md): The identity behind the calling ozk_ key: user id, tier and key label.
- [Four wires](https://www.plungeai.com/docs/api-reference/four-wires.md): One payload on four wires. Send JSON or YAML, read the answer as json, yaml, markdown or text, on every execute route and on errors, with the same fields in each.
- [MCP server overview](https://www.plungeai.com/docs/mcp-reference/overview.md): Endpoint, versions, auth and sessions.
- [plungeai_execute_workflow](https://www.plungeai.com/docs/mcp-reference/tools/plungeai_execute_workflow.md): Execute a CNL workflow (saved workflow_id or ad-hoc workflow_yaml).
- [plungeai_execute_agent](https://www.plungeai.com/docs/mcp-reference/tools/plungeai_execute_agent.md): Execute a single PROMPT-DRIVEN agent, e.g.
- [plungeai_get_tool_contract](https://www.plungeai.com/docs/mcp-reference/tools/plungeai_get_tool_contract.md): The exact invocation contract for one registry agent: JSON Schema for its parameters, operations (with approval gates), worked YAML examples, output shape, and LIVE credential status for the acting user (platform-managed vs "connect Google first").
- [plungeai_execute_tool](https://www.plungeai.com/docs/mcp-reference/tools/plungeai_execute_tool.md): Execute one structured tool-agent directly with typed params: {agent_id, operation?, params}.
- [plungeai_run_mission](https://www.plungeai.com/docs/mcp-reference/tools/plungeai_run_mission.md): Run a bounded autonomous agent mission (loop agent): give a goal, optional tool fence and iteration cap.
- [plungeai_learn](https://www.plungeai.com/docs/mcp-reference/tools/plungeai_learn.md): Manage your private skill library.
- [plungeai_list_agents](https://www.plungeai.com/docs/mcp-reference/tools/plungeai_list_agents.md): Discover platform building-block agents from the live registry (the capability catalog).
- [plungeai_list_workflows](https://www.plungeai.com/docs/mcp-reference/tools/plungeai_list_workflows.md): List your saved workflows — what users usually mean by "my agents". No args shows your folders (rubrics) + recent; filter with folder, search and/or kind.
- [plungeai_get_result](https://www.plungeai.com/docs/mcp-reference/tools/plungeai_get_result.md): Retrieve the result of one of your executions (by `execution_id`) — for conversational runs this includes the FULL conversation thread (all follow-up turns), same as Studio shows.
- [plungeai_get_workflow_status](https://www.plungeai.com/docs/mcp-reference/tools/plungeai_get_workflow_status.md): Check the status of one of your executions (self-heals stuck runs). Returns structured content too, including `continuation` when the run is paused awaiting user approval or an answer — relay that to the user and use plungeai_continue.
- [plungeai_workflow](https://www.plungeai.com/docs/mcp-reference/tools/plungeai_workflow.md): Manage your workflows: action create|get|update|delete|save_version|list_versions|get_version|restore_version|a2a_door (door_action mint|get|pause|resume|revoke — the workflow's Agent2Agent door).
- [plungeai_executions](https://www.plungeai.com/docs/mcp-reference/tools/plungeai_executions.md): Browse your execution history: action list|get|output|conversation|files|delete|cancel|steer.
- [plungeai_followup](https://www.plungeai.com/docs/mcp-reference/tools/plungeai_followup.md): Ask a follow-up about a completed execution (continues its agent session or researches with prior context). If the execution is still running, your message is queued and injected at its next turn (steer); if finished, it continues the conversation.
- [plungeai_continue](https://www.plungeai.com/docs/mcp-reference/tools/plungeai_continue.md): Continue a paused conversation: answer a question (message) or approve a pending action (approve:true). Only pass approve:true after the user explicitly confirmed — never approve on your own. To deny or change course, pass their words as message.
- [plungeai_chat](https://www.plungeai.com/docs/mcp-reference/tools/plungeai_chat.md): Persistent chat with the PlungeAI assistant (platform tools + web search). action send|new|list_sessions|history. Conversations appear in Studio and the CLI.
- [plungeai_build_workflow](https://www.plungeai.com/docs/mcp-reference/tools/plungeai_build_workflow.md): Generate a new workflow from a goal, or refine an existing one (workflow_id + instruction), via the platform builder. Saves it so it appears everywhere (live sync).
- [plungeai_memory](https://www.plungeai.com/docs/mcp-reference/tools/plungeai_memory.md): Long-term memory scoped to you: action recall|remember|search_runs|get_run|forget.
- [plungeai_templates](https://www.plungeai.com/docs/mcp-reference/tools/plungeai_templates.md): Workflow templates: action list|get|use. "use" creates a workflow from the template (optional name + folder).
- [plungeai_schedule](https://www.plungeai.com/docs/mcp-reference/tools/plungeai_schedule.md): Scheduled (cron) jobs: action stats|list|get|create|update|pause|resume|delete|run_now|runs|wake.
- [plungeai_whoami](https://www.plungeai.com/docs/mcp-reference/tools/plungeai_whoami.md): Show the authenticated identity: user id, tier, key label, rate-limit window.
- [plungeai_companies](https://www.plungeai.com/docs/mcp-reference/tools/plungeai_companies.md): Your companies (campuses compiled from saved campus + building + office documents), the same as the One API /v1/companies: action list|apply|layout|snapshot|events|ingest|slice; items item_create|item_get|item_pause|item_resume|item_retry|item_cancel|item_steer (item_id, text; item_get returns the…
- [plungeai_connections](https://www.plungeai.com/docs/mcp-reference/tools/plungeai_connections.md): Your connected accounts, the same as the One API /v1/connections: action list (provider, method, status — never a credential)|add (provider + api_key[, api_secret] for a key-based provider)|remove (provider)|link (provider[, return_url]: a signed single-use Studio link, 15 minutes, to connect an…
- [PlungeAI Agents](https://www.plungeai.com/docs/mcp-reference/resources/agents-list.md): Live agent registry (markdown)
- [Agent Categories](https://www.plungeai.com/docs/mcp-reference/resources/agents-categories.md): Live registry categories with agent counts (markdown)
- [Personas](https://www.plungeai.com/docs/mcp-reference/resources/personas-list.md): Live persona registry (markdown)
- [Your Workflows](https://www.plungeai.com/docs/mcp-reference/resources/workflows-list.md): Your saved workflows (markdown)
- [Workflow Authoring Guide](https://www.plungeai.com/docs/mcp-reference/resources/docs-workflow-authoring.md): Author, validate, and save CNL workflows (full skill bundle)
- [Agents by category](https://www.plungeai.com/docs/mcp-reference/resources/agents-by-category.md): Resource template plungeai://agents/{category}, read with resources/read.
- [Workflow YAML by id](https://www.plungeai.com/docs/mcp-reference/resources/workflow-yaml.md): Resource template plungeai://workflows/{id}, read with resources/read.
- [Execution result by id](https://www.plungeai.com/docs/mcp-reference/resources/execution-result.md): Resource template plungeai://executions/{id}, read with resources/read.
- [plungeai](https://www.plungeai.com/docs/mcp-reference/prompts/plungeai.md): The /plungeai prompt: PlungeAI MCP.
- [initialize](https://www.plungeai.com/docs/mcp-reference/protocol/initialize.md): Negotiate the protocol version and read the server capabilities.
- [tools/list](https://www.plungeai.com/docs/mcp-reference/protocol/tools-list.md): List the tools your key can call; there is no pagination.
- [tools/call](https://www.plungeai.com/docs/mcp-reference/protocol/tools-call.md): Call one tool; the answer streams as SSE.
- [resources/list](https://www.plungeai.com/docs/mcp-reference/protocol/resources-list.md): List the five static resources.
- [resources/templates/list](https://www.plungeai.com/docs/mcp-reference/protocol/resources-templates-list.md): List the three resource templates.
- [resources/read](https://www.plungeai.com/docs/mcp-reference/protocol/resources-read.md): Read one resource by URI; an unknown URI answers -32002.
- [prompts/list](https://www.plungeai.com/docs/mcp-reference/protocol/prompts-list.md): List the one prompt, plungeai.
- [prompts/get](https://www.plungeai.com/docs/mcp-reference/protocol/prompts-get.md): Get a prompt by name; an unknown name answers -32602.
- [ping](https://www.plungeai.com/docs/mcp-reference/protocol/ping.md): Check the connection; the result is an empty object.
- [logging/setLevel](https://www.plungeai.com/docs/mcp-reference/protocol/logging-set-level.md): Accepted and answered with an empty object; the level is not kept.
- [Get balance](https://www.plungeai.com/docs/account-api/balance/get-balance.md): Dashboard view: the wallet balance, top-ups, spend and auto-recharge setting. (planned)
- [Add to balance](https://www.plungeai.com/docs/account-api/balance/add-to-balance.md): Dashboard view: top up the wallet through Stripe Checkout. (planned)
- [Create key](https://www.plungeai.com/docs/account-api/keys/create-key.md): Create an ozk_ key in the Dashboard. (planned)
- [Delete key](https://www.plungeai.com/docs/account-api/keys/delete-key.md): Dashboard view: revoke a key in the Dashboard. (planned)
- [Get usage](https://www.plungeai.com/docs/account-api/usage/get-usage.md): Dashboard view: runs, tokens and cost by user, workflow, model or channel. (planned)
- [Who am I](https://www.plungeai.com/docs/account-api/identity/whoami.md): Your identity, tier, key label and rate-limit window over MCP with plungeai_whoami.
- [Agent Skills](https://www.plungeai.com/docs/skills.md): 33 skills, version 3.2.0
- [choose-your-plungeai-door](https://www.plungeai.com/docs/skills/choose-your-plungeai-door.md): Picks the right PlungeAI entry point before you write anything — the MCP server (https://mcp.plungeai.com/v1) for live agent operation, the One API (https://api.plungeai.com) for code you write or generate, the Ocean CLI for a terminal or CI workflow, or Ocean Studio for a human building visually…
- [plungeai-api-setup](https://www.plungeai.com/docs/skills/plungeai-api-setup.md): Setup for the PlungeAI One API (https://api.plungeai.com, v2.3.0) — a self-service ozk_ key, the Bearer/X-API-Key header, your first curl call, the live OpenAPI 3.1 contract at /v1/openapi.json, typed-client codegen, the three API levels (compatible wire, standard REST incl.
- [Bots, executions, schedules, connections and the Agent Call door — over REST](https://www.plungeai.com/docs/skills/plungeai-api-setup/references/bots-and-door.md): One API 2.3.0 puts everything a saved bot needs on REST, under the same ozk key (Authorization: Bearer ozkYOURKEY).
- [Route map — the planes that are not bots, one line per operation](https://www.plungeai.com/docs/skills/plungeai-api-setup/references/route-map.md): The One API 2.3.0 has 114 operations.
- [SDK & codegen — typed clients, snippets, and the AGENTS.md block](https://www.plungeai.com/docs/skills/plungeai-api-setup/references/sdk-and-codegen.md): The supported integration stance, in order of preference:
- [plungeai-cli-setup](https://www.plungeai.com/docs/skills/plungeai-cli-setup.md): Install and log in to the PlungeAI Ocean CLI (ocean-cli, npm package @plungeai/ocean) and run your first commands.
- [ocean-cli — flows an agent runs end to end](https://www.plungeai.com/docs/skills/plungeai-cli-setup/references/agent-flows.md): Skill: plungeai-cli-setup. Replace <…> with real values; confirm any flag with ocean-cli <noun> <verb> --help.
- [ocean-cli — install, credentials, config, doctor](https://www.plungeai.com/docs/skills/plungeai-cli-setup/references/auth-and-setup.md): Skill: plungeai-cli-setup. The full verb tree is in the ocean-cli skill (references/verbs.md).
- [ocean-cli — the nouns](https://www.plungeai.com/docs/skills/plungeai-cli-setup/references/commands.md): Grammar: ocean-cli <noun> <verb> [ARGS] [--flags]. Every flag: see the ocean-cli skill's references/verbs.md (generated from --help), or run ocean-cli <noun> <verb> --help (every leaf carries an example).
- [plungeai-sdk-setup](https://www.plungeai.com/docs/skills/plungeai-sdk-setup.md): Install and use the official PlungeAI One API SDKs — TypeScript `@plungeai/one-api` (npm), Python `plungeai` (PyPI), Go `github.com/PlungeAI/plungeai-go` and Rust `plungeai` (crates.io) — for the One API at https://api.plungeai.com: key from PLUNGEAI_API_KEY, first whoami and agents.execute call…
- [Per-language detail — the four One API SDKs](https://www.plungeai.com/docs/skills/plungeai-sdk-setup/references/per-language.md): Shared by all four: the key comes from PLUNGEAIAPIKEY; base URL https://api.plungeai.com; retries 2 with exponential backoff honouring Retry-After on connection errors, timeouts, 408, 429 and ≥ 500 — never on 409 or 424 (semantic answers: approvalrequired, duplicateexecutionid, a missing…
- [plungeai-mcp-setup](https://www.plungeai.com/docs/skills/plungeai-mcp-setup.md): Connect and operate the PlungeAI MCP server (https://mcp.plungeai.com/v1) — endpoint and Bearer ozk_/X-API-Key auth, a generic MCP client config (native remote/HTTP, or the mcp-remote stdio bridge), plungeai_whoami, the structured-outcome envelope and trust fences, the full plungeai_* tool index…
- [Identity & errors — whoami, the auth model, outcome envelope, trust fences](https://www.plungeai.com/docs/skills/plungeai-mcp-setup/references/identity-and-errors.md): ---
- [The 22 tools — parameters and every action](https://www.plungeai.com/docs/skills/plungeai-mcp-setup/references/tool-actions.md): Names, parameters and action values below are the zod schemas the server validates against; tools/list is still authoritative for the key in hand (a fenced key sees fewer tools). The One API twin of each family is in plungeai-api-setup.
- [ocean-cli](https://www.plungeai.com/docs/skills/ocean-cli.md): Drive PlungeAI Ocean from a terminal with the ocean-cli command (package @plungeai/ocean): web search, extract and deep research, registry agents and tool agents, saved workflows and bots, executions, missions, schedules and their triggers, memory, templates, the registry, and the Studio account…
- [ocean-cli — every command and flag (generated)](https://www.plungeai.com/docs/skills/ocean-cli/references/verbs.md): Reference page of the ocean-cli skill.
- [plungeai-agents](https://www.plungeai.com/docs/skills/plungeai-agents.md): Run a PlungeAI registry agent: recognize the two kinds (prompt-driven vs structured tool-agents), list them (`GET /v1/agents`), execute a prompt-driven one sync or async (`plungeai_execute_agent` MCP / `POST /v1/agents/{id}/execute` REST / `ocean-cli agents run`, incl.
- [Executing agents over MCP — execute_agent, get_result](https://www.plungeai.com/docs/skills/plungeai-agents/references/mcp-execute-and-result.md): Two execution styles, chosen by the agent's card:
- [Agents — the registry, discovery, and execution](https://www.plungeai.com/docs/skills/plungeai-agents/references/registry.md): An agent is a deployed capability with a uniform interface: it accepts a task, does one job well (search the web, call an LLM, convert a document, post to Slack, enrich a CRM contact), and stores its result where the platform can hand it to the next step.
- [Agents plane — /v1/agents](https://www.plungeai.com/docs/skills/plungeai-agents/references/rest-agents-plane.md): Execute any active platform agent with a plain prompt. The gateway wraps your call in a one-task workflow, so every execution yields a workflowid + taskid pair — that pair is the handle for async redemption and for traces.
- [plungeai-campaigns](https://www.plungeai.com/docs/skills/plungeai-campaigns.md): Run a list to completion on PlungeAI: the campaign ledger (claim/complete/fail/retry), the campaign-config (list source, cycle, cadence, retries, delivery), and how a campaign keeps going via cron or self-scheduling runAgain.
- [Campaigns — running a list to completion (the campaign ledger)](https://www.plungeai.com/docs/skills/plungeai-campaigns/references/campaigns.md): A campaign claims a list of items (a data-table query, an agent's lister output, an uploaded CSV, or an inline list), runs each item through a CNL pipeline with per-item retries, and repeats on a cadence until the list ("cycle") is drained — then either re-cycles (refill/reset) or hands off to…
- [plungeai-discovery](https://www.plungeai.com/docs/skills/plungeai-discovery.md): Find the right thing on PlungeAI's live registry before building anything: agents, structured tools, models, skills, personas, connectors, and workflow templates, via hybrid semantic + keyword search (`plungeai_list_agents` MCP / `GET /v1/discovery/search` REST / `ocean-cli discovery search`)…
- [Discovery over MCP — list_agents, get_tool_contract, templates (listing)](https://www.plungeai.com/docs/skills/plungeai-discovery/references/list-and-contract.md): The registry is LIVE: agents come from the registry service at request time, no static manifest.
- [Discovery — /v1/discovery](https://www.plungeai.com/docs/skills/plungeai-discovery/references/search-and-recommend.md): Discovery is the live catalog of everything the platform can do — agents, workflows, MCP servers, connectors, models — with hybrid semantic + keyword search ranked server-side.
- [plungeai-memory](https://www.plungeai.com/docs/skills/plungeai-memory.md): Read and write PlungeAI's per-user long-term memory over MCP (plungeai_memory: recall/remember/search_runs/get_run), the CLI (`ocean-cli memory`) and the One API (`/v1/memory/recall`, `/remember`, `/forget`, `/runs`), and save or distill a skill from a session (plungeai_learn, `POST…
- [Memory — run data (SharedMemory) vs long-term memory. Two systems, never confuse them](https://www.plungeai.com/docs/skills/plungeai-memory/references/memory.md): PlungeAI has TWO memory systems with different jobs:
- [plungeai-missions](https://www.plungeai.com/docs/skills/plungeai-missions.md): Run bounded autonomous PlungeAI agent missions (type: harness) — a goal, a tool fence, an iteration cap, and self-checked success criteria, via plungeai_run_mission, `ocean-cli missions run`, or a harness task over the One API (`POST /v1/workflows/execute`, the Agent Call door `POST /v1/execute`).
- [Missions — bounded autonomous agent runs (type: harness)](https://www.plungeai.com/docs/skills/plungeai-missions/references/missions.md): A mission bounds what an agent may do for ONE goal: a standing purpose, a fenced tool set, an iteration cap, optional identity/knowledge injection, and self-checked success criteria.
- [plungeai-models](https://www.plungeai.com/docs/skills/plungeai-models.md): Model routing on PlungeAI: how agents/workflows/missions resolve a model through the platform's provider factory (`model`/`provider` fields on a task, mission or `POST /v1/agents/{id}/execute`), and the separate OpenAI-compatible money-plane API (`https://api.plungeai.com/v1/chat/completions`…
- [Models plane — /v1/chat/completions, /v1/embeddings, /v1/models](https://www.plungeai.com/docs/skills/plungeai-models/references/money-plane.md): The OpenAI-compatible surface ("money plane"). Auth is the same ozk key as the rest of the API, sent as Authorization: Bearer ozkYOURKEY only (from Ocean Dashboard → One API → Keys). Errors use the OpenAI error shape {"error":{"message","type","code","requestid"}}.
- [Models — provider factory inside runs, money plane for your code](https://www.plungeai.com/docs/skills/plungeai-models/references/provider-factory.md): PlungeAI touches models in two distinct places. Keep them apart:
- [plungeai-platform](https://www.plungeai.com/docs/skills/plungeai-platform.md): THE PlungeAI (Ocean) platform capability map: a growing live registry of agents and structured tools, CNL multi-agent workflows, bounded harness missions, injectable skills/plugins/experts/personas, model routing with an OpenAI-compatible inference API, cron scheduling, per-user long-term memory…
- [plungeai-results-traces](https://www.plungeai.com/docs/skills/plungeai-results-traces.md): Debug and observe PlungeAI runs: live SSE events, plungeai_get_workflow_status / plungeai_executions history, persisted GET /v1/traces/{id} spans and gateway request cost, the HITL conversation loop (plungeai_continue/plungeai_followup/plungeai_chat), and outbound MCP door runs (POST…
- [Conversation — chat, followup, continue (and the ⏸ HITL loop)](https://www.plungeai.com/docs/skills/plungeai-results-traces/references/conversation.md): Three distinct conversation surfaces — pick by what the user is doing:
- [MCP plane — /v1/mcp](https://www.plungeai.com/docs/skills/plungeai-results-traces/references/mcp-runs.md): Two directions in one plane:
- [Observability — watching, debugging, and pricing platform runs](https://www.plungeai.com/docs/skills/plungeai-results-traces/references/observability.md): Every execution on PlungeAI is observable at four altitudes: live events while it runs, an execution record after it finishes, a persisted span-level trace, and the gateway's own request log with cost. Debugging is reading these in order — not re-running the workload to "see what happens".
- [Traces — GET /v1/traces/{id}](https://www.plungeai.com/docs/skills/plungeai-results-traces/references/traces.md): The observability plane: one id follows a request across every internal hop. (This is the traces half of the One API's discovery+traces route group — for /v1/discovery/ see plungeai-discovery.)
- [plungeai-scheduling](https://www.plungeai.com/docs/skills/plungeai-scheduling.md): Cron-schedule PlungeAI workflows, agent queries, pre-built agent cards, and condition-watching heartbeats via plungeai_schedule, with full run history and retries.
- [Scheduling — cron jobs for workflows, agents, and missions](https://www.plungeai.com/docs/skills/plungeai-scheduling/references/scheduling.md): The scheduler runs platform work unattended on cron expressions: a saved workflow every morning, an agent query hourly, a pre-built agent card nightly.
- [plungeai-skills-plugins](https://www.plungeai.com/docs/skills/plungeai-skills-plugins.md): Declare and understand PlungeAI's capability-injection fields on a type: harness task or plungeai_run_mission — skills, experts, persona, backgrounds, plugins, and MCP servers — including eager-vs-deferred budgets and degrade-to-warning failure semantics, how to look the ids up over REST (`GET…
- [Experts, personas, backgrounds — shaping WHO the agent is in a run](https://www.plungeai.com/docs/skills/plungeai-skills-plugins/references/experts-personas.md): Three capability kinds shape an agent's identity and framing (as opposed to skills, which shape its methods). All three inject into the front of the system prompt, in a fixed order, before anything else the run adds:
- [Plugins — bundles of skills, MCP servers, and scripts injected as one unit](https://www.plungeai.com/docs/skills/plungeai-skills-plugins/references/plugins.md): A plugin is a Claude-Code-format bundle stored on the platform: a directory tree containing any number of SKILL.md skills, an optional .mcp.json (or manifest mcpServers) documenting the MCP servers its skills were written for, and executable Python scripts.
- [Skills — injectable instruction packs for agent runs](https://www.plungeai.com/docs/skills/plungeai-skills-plugins/references/skills.md): A skill is a markdown instruction pack (the Agent Skills SKILL.md format: frontmatter name + description, then the body) stored on the platform and injected into agent runs.
- [plungeai-tools-connectors](https://www.plungeai.com/docs/skills/plungeai-tools-connectors.md): Call PlungeAI structured tool-agents with typed parameters against a published invocation contract: fetch the contract (`plungeai_get_tool_contract` / `GET /v1/tools/{id}`), execute with typed `params` (`plungeai_execute_tool` / `POST /v1/tools/{id}/execute`), see which credential a tool runs on…
- [Tools — structured tool-agents and their contracts](https://www.plungeai.com/docs/skills/plungeai-tools-connectors/references/contract-and-execution.md): A tool on PlungeAI is a structured agent: instead of free-text prompts it takes typed parameters against a published contract — named operations, a JSON Schema for inputs, worked examples, and per-operation approval gates.
- [Executing tools over MCP — execute_tool](https://www.plungeai.com/docs/skills/plungeai-tools-connectors/references/mcp-execute-tool.md): Structured tool-agents (cards with a Parameters table — posting, document conversion, weather, data-table CRUD, calendar operations, payment actions) take typed fields against a published contract, not prose.
- [Tools plane — /v1/tools](https://www.plungeai.com/docs/skills/plungeai-tools-connectors/references/rest-tools-plane.md): Every active agent is also callable as a tool with a machine-checkable invocation contract. The flow is always: discover → inspect the contract → execute. This plane runs the platform's trust fence — gated and money operations refuse unattended execution by design.
- [plungeai-workflows](https://www.plungeai.com/docs/skills/plungeai-workflows.md): Build, validate, test, and save PlungeAI (Ocean Studio) workflows in CNL YAML.
- [Workflows plane — /v1/workflows](https://www.plungeai.com/docs/skills/plungeai-workflows/references/api.md): Run multi-agent CNL workflows: inline (send the workflow document in the request), saved (reference a workflow id saved in Ocean Studio), each with an optional SSE streaming variant, plus a results-redemption route.
- [Getting a workflow into PlungeAI — three channels](https://www.plungeai.com/docs/skills/plungeai-workflows/references/channels.md): Connect once (self-service ozk key from Dashboard → One API → Keys, https://dashboard.plungeai.com):
- [CNL Workflow Reference (engine v6) — PlungeAI](https://www.plungeai.com/docs/skills/plungeai-workflows/references/cnl-spec.md): CNL (Cognitive Natural Language) is PlungeAI's YAML workflow language: you declare tasks and how they compose (parallel, sequential, batch, debate, harness, …), and the engine dispatches them to platform agents with automatic data flow between steps.
- [Workflows — execute_workflow, get_workflow_status, list_workflows, workflow, build_workflow, executions](https://www.plungeai.com/docs/skills/plungeai-workflows/references/mcp.md): Workflows are CNL YAML run by the platform engine.
- [Workflows — CNL orchestration: what it is and how to run it](https://www.plungeai.com/docs/skills/plungeai-workflows/references/overview.md): A workflow is a YAML document (CNL — Cognitive Natural Language) that the engine executes as a DAG of agent calls: parallel fan-out, sequential pipelines, unlimited nesting, conditions, batches, debates, and bounded autonomous missions.
- [CNL recipes — pick the shape, then adapt](https://www.plungeai.com/docs/skills/plungeai-workflows/references/recipes.md): Full runnable versions live in examples/. Two composition rules apply to all of them:
- [plungeai-in-bolt](https://www.plungeai.com/docs/skills/plungeai-in-bolt.md): Connect Bolt.new to PlungeAI (Ocean Studio) over MCP — the Connectors → Custom MCP server form, the all-tools/all-projects toggle behavior, keeping the shipped app's key server-side, and a plungeai_whoami + plungeai_list_agents verify.
- [plungeai-in-claude-ai](https://www.plungeai.com/docs/skills/plungeai-in-claude-ai.md): Connect claude.ai web or Claude Desktop to PlungeAI (Ocean Studio) — Desktop live tools via the mcp-remote bridge in claude_desktop_config.json (OAuth isn't available yet, hence the bridge), claude.ai web via skill.zip upload, and a plungeai_whoami + plungeai_list_agents verify for Desktop.
- [plungeai-in-claude-code](https://www.plungeai.com/docs/skills/plungeai-in-claude-code.md): Connect the Claude Code CLI to PlungeAI (Ocean Studio) over MCP — 'claude mcp add' one-liner, project-scoped .mcp.json with an env-var key, the skills/plugin install path, and a plungeai_whoami + plungeai_list_agents verify.
- [plungeai-in-codex](https://www.plungeai.com/docs/skills/plungeai-in-codex.md): Connect OpenAI Codex CLI to PlungeAI (Ocean Studio) over MCP — native streamable-HTTP in ~/.codex/config.toml (env-var or static bearer token), the codex mcp add terminal command, the mcp-remote bridge fallback, and a plungeai_whoami + plungeai_list_agents verify.
- [plungeai-in-cursor](https://www.plungeai.com/docs/skills/plungeai-in-cursor.md): Connect Cursor to PlungeAI (Ocean Studio) over MCP — the one-click install-page deeplink or a ~/.cursor/mcp.json entry, Agent/Plan-mode tool behavior, the ~40-tool cap, and a plungeai_whoami + plungeai_list_agents verify.
- [plungeai-in-gemini-cli](https://www.plungeai.com/docs/skills/plungeai-in-gemini-cli.md): Connect Gemini CLI to PlungeAI (Ocean Studio) over MCP — a ~/.gemini/settings.json entry using httpUrl (not url, which is SSE-only and 405s), the mcp-remote bridge fallback, /mcp reload after edits, and a plungeai_whoami + plungeai_list_agents verify.
- [plungeai-in-lovable](https://www.plungeai.com/docs/skills/plungeai-in-lovable.md): Connect Lovable to PlungeAI (Ocean Studio) — a personal chat connector (any plan) so Lovable's chat can operate PlungeAI via MCP while building, and a workspace-admin app connector so shipped apps call the One API in production with attached auth, plus a plungeai_whoami + plungeai_list_agents…
- [plungeai-in-opencode](https://www.plungeai.com/docs/skills/plungeai-in-opencode.md): Connect OpenCode to PlungeAI (Ocean Studio) over MCP — an opencode.json mcp.plungeai entry with type: remote, {env:VAR} variable substitution for a committed project config, and a plungeai_whoami + plungeai_list_agents verify.
- [plungeai-in-replit](https://www.plungeai.com/docs/skills/plungeai-in-replit.md): Connect Replit Agent to PlungeAI (Ocean Studio) over MCP — the one-click install-page link, the Integrations → MCP Servers form, keeping the Agent's MCP key separate from a deployed app's Replit Secret, and a plungeai_whoami + plungeai_list_agents verify.
- [plungeai-in-v0](https://www.plungeai.com/docs/skills/plungeai-in-v0.md): Connect v0 (Vercel) to PlungeAI (Ocean Studio) over MCP — the + menu → MCPs form, why the generated Next.js app must call PlungeAI through a server Route Handler (v0 apps can't call MCP directly), and a plungeai_whoami + plungeai_list_agents verify.
- [plungeai-in-vscode](https://www.plungeai.com/docs/skills/plungeai-in-vscode.md): Connect VS Code (GitHub Copilot agent mode) to PlungeAI (Ocean Studio) over MCP — the code --add-mcp CLI command, a committed-safe .vscode/mcp.json with an input-prompted key, the 128-tools-per-request cap, and a plungeai_whoami + plungeai_list_agents verify.
- [plungeai-in-windsurf](https://www.plungeai.com/docs/skills/plungeai-in-windsurf.md): Connect Windsurf (Cascade) to PlungeAI (Ocean Studio) over MCP — a ~/.codeium/windsurf/mcp_config.json entry using serverUrl, the mcp-remote bridge fallback for stdio-only builds, the 100-tool cap, and a plungeai_whoami + plungeai_list_agents verify.
- [plungeai-agentic-agent](https://www.plungeai.com/docs/skills/plungeai-agentic-agent.md): Design and emit ONE bounded agentic agent for PlungeAI (Ocean Studio) as a single `type: harness` mission — purpose, allowed_tools fence, permissions gates (deny/ask), skills/plugins/MCP/persona declarations, effort or turn cap, success criteria — then hand it to Studio as CNL YAML.
- [The fence — tools, agents, and fan-out guards](https://www.plungeai.com/docs/skills/plungeai-agentic-agent/references/fence.md): allowedtools is a hard whitelist — only listed tools ever reach the LLM; an out-of-fence call is refused by the runtime, not merely discouraged. Omit it and one-agent offers every tool (the 8-tool default fence is universal-agent's only) — so always list the fence you mean.
- [Harness task — the full mission contract](https://www.plungeai.com/docs/skills/plungeai-agentic-agent/references/harness-task.md): Bot-only keys (peers, posture, review, maxruntimes, workspace, permissionlocks) are plungeai-bot-agent's.
- [plungeai-bot-agent](https://www.plungeai.com/docs/skills/plungeai-bot-agent.md): Design and emit ONE PlungeAI (Ocean Studio) bot agent — a scheduled, unattended `type: harness` mission that reports to the user's channels (in-app, email, Slack, Telegram, WhatsApp, Discord, Teams) — as CNL YAML plus a bot-config block (cron schedule, delivery targets, optional run-on-my-computer).
- [bot-config → scheduler job](https://www.plungeai.com/docs/skills/plungeai-bot-agent/references/bot-config.md): The block becomes one scheduled job that delivers taskcomplete's result to every target.
- [plungeai-campaign-agent](https://www.plungeai.com/docs/skills/plungeai-campaign-agent.md): Design and emit ONE PlungeAI (Ocean Studio) campaign agent — a long-running, list-driven, resumable agent that works an owned ledger of items in short scheduled runs until the current cycle is exhausted — as CNL YAML (a claim task plus a `type: batch` with `ledger: campaign`) and a campaign-config…
- [campaign-config reference](https://www.plungeai.com/docs/skills/plungeai-campaign-agent/references/campaign-config.md): A campaign-config fenced block sits after the CNL YAML. Studio parses it to open the ledger and create the scheduler job. Fields:
- [Changelog](https://www.plungeai.com/docs/resources/changelog.md): Planned: the dated list of PlungeAI changes. (planned)

## OpenAPI Specs
- [openapi](https://www.plungeai.com/docs/openapi.json)
- [api-live-openapi](https://api.plungeai.com/v1/openapi.json)
- [mcp-tools](https://www.plungeai.com/docs/mcp-tools.json)

## Optional
- [Get API Key](https://dashboard.plungeai.com/one-api?tab=keys)
- [OpenAPI Spec](https://www.plungeai.com/docs/openapi.json)
- [SDKs](https://www.plungeai.com/docs/sdks/typescript)
- [Ocean CLI](https://www.plungeai.com/docs/developer-tools/cli)