Hotato MCP server

by attenlabs·io.github.attenlabs/hotato·v1.9.0·2 stars

No reviews yet

Open-source, self-hosted conversation QA for voice agents. MIT.

A86/100grade A

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

A86/100

full report

Adoption

Growing

2 stars141 downloads/wk

Reviews

Write one

Nobody has reviewed Hotato yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Hotato tools (16, 3 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

artifact_verify
Verify a contract bundle's authenticity + evidence without trusting it. Read-only.
build_server
Construct the FastMCP server with the scoring tool and the fleet tools registered.
candidate_inspect
Inspect one candidate moment: onset, measured components (severity/input_health/recurrence/novelty/covered_by_contract), and trust findings. Read-only; never labels.
candidate_list
List top candidate moments awaiting human review. Read-only; never labels.
clone_cleanup
Clone-scoped: delete a STAGING clone THIS tool created, authorized by its durable clone receipt (referenced by trial_id or receipt_id) -- never a raw clone id or display name. Never touches production.
contract_list
List contracts in a workspace. Read-only.
counterexample_compile
counterexample_reproduce
counterexample_verify
experiment_createwrite action
Clone-scoped: precommit a trial manifest from a committed battery BEFORE any capture, so the fixture universe is fixed ahead of the results. Never captures, never deploys.
experiment_propose
Propose a bounded variant set with expected effects. Read-only; does not clone, apply, or deploy.
experiment_runwrite action
Clone-scoped: recompute a before/after trial (offline, no network, no production mutation) and record a recommendation. Names any pending human-gated action.
experiment_status
Report a trial's current verdict, evidence tier, recommendation, manifest hash, and any pending human-gated action. Read-only.
fleet_status
Read the local fleet workspace rollup (counts + jobs). Read-only.
trial_explain
Explain a recorded trial's verdict, evidence tier, recommendation, and any pending human-gated action. Read-only.
voice_eval_runwrite action

Public scan report

scanner v0.1.9 · 2026-09-25 · same rubric, same numbers if you re-run it

1 medium

Code scan213 source files scanned20/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitylocal package, no credentials required12/15
Maintenancelast push 28 days ago15/15
Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10

Findings (1)

mediumeval / new Function usedexec.eval

hotato-1.9.0/src/hotato/diarize.py: …del.from_pretrained(ckpt) model.eval() except Exception as exc: r…

Overall 86/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

How Hotato compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 86/100; higher than 72% of 48,255 servers
Tools: 16; the typical server has 7
Tools that change things: 19%; typical: 0%. Fewer write tools means less an agent can break
GitHub stars: 2; more than 75% of 28,688 servers
Downloads a week: 141; more than 70% of 12,191 servers with a package

What its tools let an agent do: 12 read · 1 create · 3 change

Install Hotato in Claude Code, Cursor or VS Code

claude mcp add hotato -- uvx hotato

Add to Cursor

What the publisher says

From the Hotato repository's README, as published. We do not edit it. Read it on GitHub

hotato

Find what broke in your agent calls. Pin it and CI stays red until you fix it.

pip install hotato
hotato check --demo             # a bundled failing call: what broke, and when
hotato check ./call.wav         # then your own recording
hotato vapi health              # or your last 100 Vapi calls

Zero config. Vapi, Retell, Bland, Synthflow, Millis, or local audio. Works with any recording: mono, dual-channel, or a transcript. Timing math, not a judge. Offline. Free. MIT.

hotato.dev

What it finds

Say-do gaps: the caller interrupts to cancel (a barge-in), the agent says "canceled", the booking tool fires anyway. hotato takes the turn timing from the audio and the tool call from your OTel trace.
Latency spikes: the pause before a reply going from 800 ms to over 2 s.
Dead air: that pause reaching 5 s, or the line going quiet.
Talk-over: the agent starts a fresh utterance over the caller.

Quickstart

Vapi

pip install hotato
export VAPI_API_KEY=...
hotato vapi health --last 7d --output report.html

Open report.html: every critical incident, timestamped, and your Voice Stability Score.

Retell

export RETELL_API_KEY=...
hotato retell health --call-id CALL_ID

--call-id is required and repeatable: you name the Retell calls to pull. hotato bland health, hotato synthflow health, and hotato millis health follow the Vapi shape. Those stacks mix both voices onto one channel, so they measure silence timing, dead air and latency gaps, each finding with its measured confidence; barge-in and talk-over need two channels.

Local audio

hotato autopsy ./call.wav

Writes a self-contained HTML report to hotato-output/, plus the JSON pin reads. Open the HTML in your browser.

From finding a bug to gating on it

autopsy turns one recording into timestamped incidents. scan reads a folder and tracks the trend. When you are ready, move a finding into CI: hotato pin turns one incident into a portable failure check, and hotato prove re-runs every stored check and fails the build rather than pass on evidence it cannot re-read. Every verdict carries its own evidence across five dimensions: outcome, policy, conversation, speech, reliability.

A pinned check re-measures its own stored recording, so it holds the build red on that bug and catches an edited bundle, a loosened policy, or an engine upgrade that scores the same bytes differently. Clearing it takes a fresh recording of the same moment against the current agent: hotato drive places that call on Vapi or Twilio, and docs/RECAPTURE.md is the walkthrough for every other stack.

Pin a bug →

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Hotato: common questions

Is Hotato MCP server safe?: Yes, by our scan: it is graded A (86/100). Read the Hotato safety report
How do I install Hotato?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Hotato need an API key?: Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Hotato maintained?: The last commit was 68 days ago (2026-08-28). The latest release is v1.9.0.
How does Hotato compare with other MCP servers?: safety score 86/100 (higher than 72% of 48,255 servers); tools 16 (the typical server has 7); tools that change things 19% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.