MCP endpoint
A native Model Context Protocol server for this app. Point any MCP client at this URL with your api key as the bearer token and the agent's permitted surface appears as tools. One key is one server, scoped to that key's agent. There is no separate MCP configuration: the tools are the same policy-derived surface `GET /agent/tools` returns, over the same execution core, with the same halt on high-risk steps. Supported methods include `initialize`, `tools/list`, and `tools/call`.
Authorization
bearerAuth Authorization for API
In: header
Path Parameters
Your app's unique id. Find it in the console under the app's Settings, or in the URL of any app page.
uuidRequest Body
application/json
TypeScript Definitions
Use the request body type in TypeScript.
Response Body
application/json
application/json
curl -X POST "https://example.com/497f6eca-6276-4993-bfeb-53cbbbba6f08/mcp" \ -H "Content-Type: application/json" \ -d '{ "jsonrpc": "2.0", "method": "tools/list" }'{ "jsonrpc": "2.0", "id": "string", "result": {}, "error": { "code": 0, "message": "string" }}Call a tool
Runs exactly this tool, with no model in the loop — deterministic, and cheaper than an orchestrated run when you already know what you want done. The body is the tool's arguments. It accepts `{ "input": { … } }`, `{ "arguments": { … } }`, or the bare argument object. **Governance still applies.** A tool your policy marks high-risk does not execute here either: the response is `202` with a `runUid`, the call waits in the approval inbox, and you poll the run for its outcome. The direct door is faster, not looser. Equivalent to MCP `tools/call`.
MCP over GET (not supported)
MCP here is request/response over POST. There is no SSE transport on this endpoint.