List the MCP tools available to the chat surface - Feather

GET

/

v1

/

mcp-chat

/

tools

List the MCP tools available to the chat surface

curl --request GET \
  --url https://api-sandbox.featherhq.com/v1/mcp-chat/tools \
  --header 'x-api-key: <api-key>'

{
  "tools": [
    {
      "name": "<string>",
      "description": "<string>",
      "input_schema": {}
    }
  ]
}

Authorizations

x-api-key

string

header

required

Response

200 - application/json

Successful Response

Response body for GET /v1/mcp-chat/tools.

tools

ToolInfo · object[]

required

Show child attributes

Stream an LLM chat turn that uses the MCP server as its toolbeltSSE stream of one chat turn. The LLM (Claude) sees every tool registered on our MCP server. When the model wants a tool, we dispatch it via ``mcp.call_tool`` — same code path as remote MCP clients hitting ``/mcp/`` — and feed the result back. ``end_user_id`` (optional) pins all end-user-scoped tool calls to that contact. The endpoint streams an event-stream of: - ``text_delta`` — incremental assistant text (append to the bubble). - ``tool_call`` — model decided to call a tool (name, input). - ``tool_result`` — JSON-string result (or error). - ``turn_end`` — one Claude turn finished (may loop again for tools). - ``done`` — full turn complete. - ``error`` — fatal; stream closes. No RBAC dependency on this endpoint itself — tools enforce their own permissions via the ``@cx_tool`` registry, so a viewer-role caller chatting here can only invoke the read tools.

⌘I

List the MCP tools available to the chat surface

curl --request GET \
  --url https://api-sandbox.featherhq.com/v1/mcp-chat/tools \
  --header 'x-api-key: <api-key>'

{
  "tools": [
    {
      "name": "<string>",
      "description": "<string>",
      "input_schema": {}
    }
  ]
}