Home/Docs/MCP tool

The MCP tool

Hotato exposes exactly one MCP tool: score, read back failures, propose a fix. Same JSON as the CLI, honest scope inline.

Run the server

Optional MCP extra; CLI stays dependency-free. Zero-install:

bash
uvx --from "hotato[mcp]" hotato-mcp

# or, if installed
python -m hotato.mcp_server

Runs over stdio, one tool: voice_eval_run. Fully local; nothing leaves the machine.

Point a client at it

Register the stdio command; same shape everywhere:

json
# mcp client config (shape; keys vary by client)
"hotato": {
  "command": "uvx",
  "args": ["--from", "hotato[mcp]", "hotato-mcp"]
}

The one tool: voice_eval_run

Two modes: single recording or bundled battery.

ParameterPurpose
stereoTwo-channel WAV (caller/agent).
caller, agentMono WAVs, vs stereo.
suitebarge-in: bundled self-test.
stacklivekit | pipecat | vapi | generic: tunes config-fix knob names.
expectyield: agent stops. hold: backchannel.
onset_secRequired for mono; optional for stereo.
caller_channel, agent_channelDefault 0, 1.
max_talk_over_sec, max_time_to_yield_secOptional pass/fail bounds.
Honest scope, stated to the agent

Measures barge-in, turn-taking, overlap, backchannel timing, and states what it doesn't: no accuracy percentage, no speaker identification, diarization, transcription, or emotion detection. Agent sees the ceiling, not the number.

Server source: mcp_server.py.