plungeai_execute_agent

Output schema: outcome envelopeCreates an execution: yes

https://mcp.plungeai.com/v1tools/callplungeai_execute_agent

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

agentstringrequired

Maximum string length: 256

promptstringrequired

Maximum string length: 65536

personastring

Maximum string length: 256

modelstring

Default: the agent's default

Maximum string length: 256

providerstring

Default: the model's catalog provider

Maximum string length: 256

maxTokensinteger

Required range: 1 <= x <= 64000

max_tokensinteger

Required range: 1 <= x <= 64000

temperaturenumber

Required range: 0 <= x <= 2

top_pnumber

Required range: 0 <= x <= 1

reasoning_effortenum<string>

Available options: low, medium, high, xhigh

thinking_levelstring

Maximum string length: 256

streamingboolean

Default: true

session_idstring

Maximum string length: 256

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

statusenum<string>required

Available options: ok, needs_input, needs_connection, needs_api_key, needs_approval, unavailable, error

summarystringrequired

agent_idstring

operationstring

resultstring

execution_idstring

missingstring[]

warningsstring[]

remediationobject

Show child attributes

messagestringrequired

actionsobject[]required

contractobject

Execute a single PROMPT-DRIVEN agent (e.g. "llm-agent", or "skill-agent" with a persona). Pass session_id to start/continue a conversational agent. Structured tool-agents (cards with a Parameters table, e.g. markitdown, weather-agent) take typed fields, not prose — use plungeai_get_tool_contract + plungeai_execute_tool for those. Always answers with a structured outcome (never a raw error) — follow the remediation instead of retrying the identical call.

Execute a single prompt-driven agent (for example llm-agent, or skill-agent with a persona). Pass session_id to start or continue a conversational agent. Structured tool-agents (cards with a Parameters table, such as markitdown or weather-agent) take typed fields, not prose: use plungeai_get_tool_contract and plungeai_execute_tool for those. Always answers with a structured outcome, never a raw error: follow the remediation instead of retrying the identical call.

Returns. ok with the agent's output and the execution-id footer. unavailable for an unknown or inactive agent, with live alternatives and no run created. needs_input for a model that is not in the catalog (Unknown model `<id>` … Nothing was executed.) with up to five near matches. needs_approval / needs_input when the agent pauses. Failures are classified into an outcome.

Runs a model and costs credits (not verified here):

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_execute_agent","arguments":{"user_request":"ask llm-agent what a Durable Object is","agent":"llm-agent","prompt":"In one sentence: what is a Cloudflare Durable Object?","model":"claude-sonnet-4-5","max_tokens":80}}}'

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.

import json import os import requests response = requests.post( "https://mcp.plungeai.com/v1", headers={ "Authorization": f"Bearer {os.environ['PLUNGE_API_KEY']}", "Accept": "application/json, text/event-stream", "Content-Type": "application/json", }, json={ "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "plungeai_execute_agent", "arguments": { "agent": "<string>", "prompt": "<string>", }, }, }, ) for line in response.text.splitlines(): if line.startswith("data: "): print(json.loads(line[6:]))

import { Client } from '@modelcontextprotocol/sdk/client/index.js' import { StreamableHTTPClientTransport } from '@modelcontextprotocol/sdk/client/streamableHttp.js' const transport = new StreamableHTTPClientTransport(new URL('https://mcp.plungeai.com/v1'), { requestInit: { headers: { Authorization: `Bearer ${process.env.PLUNGE_API_KEY}` } }, }) const client = new Client({ name: 'my-app', version: '1.0.0' }) await client.connect(transport) const result = await client.callTool({ name: 'plungeai_execute_agent', arguments: {"agent":"<string>","prompt":"<string>"} }) console.log(result.content)

curl -N -X POST 'https://mcp.plungeai.com/v1' \ -H "Authorization: Bearer $PLUNGE_API_KEY" \ -H 'Accept: application/json, text/event-stream' \ -H 'Content-Type: application/json' \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"plungeai_execute_agent","arguments":{"agent":"<string>","prompt":"<string>"}}}'

{ "jsonrpc": "2.0", "id": 1, "result": { "content": [ { "type": "text", "text": "<string>" } ], "structuredContent": { "status": "ok", "summary": "<string>", "agent_id": "<string>", "operation": "<string>", "result": "<string>", "execution_id": "<string>", "missing": [ "<string>" ], "warnings": [ "<string>" ], "remediation": { "message": "<string>", "actions": [ {} ] }, "contract": {} } } }

plungeai_execute_agent

Authorizations

Arguments

Output

Planned: TI-33

Planned: TI-34