For AI agents: a documentation index is available at https://docs.plungeai.com/llms.txt. Append .md to any page URL, or send Accept: text/markdown, to get markdown. Setup instructions for agents are at https://docs.plungeai.com/agents.md. Execution planes take an ozk_ key; the models plane takes an sk-ocean- key.

Documentation Index: fetch the complete documentation index at /llms.txt. Use this file to discover all available pages before exploring further.
Creates an execution: no
POSThttps://mcp.plungeai.com/v1tools/callplungeai_executions

Authorizations

Authorizationstringheader
Bearer token: Authorization: Bearer ozk_….
X-API-Keystringheader
Alternative header: X-API-Key: ozk_….

Every request needs a key, tools/list included.

Arguments

user_requeststring
The user's original request, verbatim and in their own words, before you translated it into this call. Always include it — the platform uses it for request context, routing and support diagnostics.

Maximum string length: 4000

actionenum<string>required

Available options: list, get, output, conversation, delete, cancel

execution_idstring

for every action except `list`

Maximum string length: 256

workflow_idstring

Maximum string length: 256

limitinteger

Default: 20

Required range: 1 <= x <= 100

offsetinteger

Default: 0

Required range: 0 <= x <= 100000

formatenum<string>
markdown (default): rendered for an AI reader · json: the same outcome as a JSON document in text plus structuredContent

Available options: markdown, json

Default: markdown

Output

Markdown text; format: "json" returns the same answer as a JSON document.

Browse your execution history: action list|get|output|conversation|delete|cancel. cancel stops a running execution (cooperative — it stops at its next turn or tool boundary). Outputs are final user-ready markdown (tables, threads): show them to the user verbatim and complete — never summarize or re-type them.

Browse your execution history: action list, get, output, conversation, delete or cancel. cancel stops a running execution cooperatively: it stops at its next turn or tool boundary. Outputs are final, user-ready Markdown (tables, threads): show them verbatim and complete, never summarize or re-type them.

Returns. list: # Executions (N), newest first (ID, Question, Workflow, Status, When); JSON {"executions": [{id, input, workflow_name, status, start_time, duration}]}. get: the status answer of plungeai_get_workflow_status. output: the full result of plungeai_get_result. conversation: the follow-up thread; JSON {execution_id, messages}. cancel: Cancelling execution `<id>` — … (running runs only). delete: Deleted execution `<id>`.; this cannot be undone. Details: 9.4 (opens in a new tab).

curl -s https://mcp.plungeai.com/v1 \
  -H "Authorization: Bearer $PLUNGE_API_KEY" \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"plungeai_executions","arguments":{"user_request":"show me my last 5 executions","action":"list","limit":5,"format":"json"}}}'

Two parameters recur across the tools: user_request (on every tool: a string of up to 4,000 characters, optional; clients should always send it) and format (markdown by default, or json). Both are described once in Recurring parameters on the MCP overview.

Planned: TI-33

Search is not available yet. Until it ships, use the page index or browse the sidebar.

Planned: TI-34

The docs assistant is not available yet. You can hand these docs to your own assistant instead.