Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.jeet0007/mac-voice-mcp

NPM · MAC-VOICE-MCP

Talk with your AI assistant out loud on a Mac, with on-device speech recognition (whisper.cpp).

Available components

+15 this week 96 Trust /100

Last scanned (19 hours ago)

Scores higher than 98% of npm servers

Category Communication

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 0 of 1 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to jeet0007/mac-voice-mcp). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 6 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability78
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 2039 tokens (~339/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Nov 26 0
    • Stability: 0.97 → pass security
  • 19 Nov 26 0
    • Stability: pass → 0.97 functional
  • 15 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 14 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
    • Schema quality: 382 → 339 ▲ functional
    • Package version: 0.9.0 → 0.10.0 functional
  • 13 Nov 26 +1
    • Stability: 0.97 → pass security
  • 12 Nov 26 −1
    • Stability: pass → 0.97 functional
  • 6 Nov 26 +1
    • Stability: 0.97 → pass security
  • 4 Nov 26 +14
    • Malware scan: unverified → pass ▲ security
    • Stability: pass → 0.93 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed npm/mac-voice-mcp@0.10.0

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo jeet0007/mac-voice-mcp
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/jeet0007/mac-voice-mcp/.github/workflows/publish.yml@refs/tags/v0.10.0
Rekor log index 3873903127
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:7e9d96b425389d9a116d49a3999e4c7c132a258d01f48a5ab5b051ece5f6f27fbd9808ed1bfa3ce6afdc09db178c82efa7d41fd67d9c30dd63680bbb5

Background: How many MCP packages publish verified provenance →

Dependencies 1 package
Packages resolved 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 6 exposed · ~1,563 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
call ~159

Start or end a call: a hands-free session where the microphone stays open and the user talks whenever they like, like a phone call, until they hang up. action start takes the speaker and microphone and returns the rules of the call; it says nothing aloud, so greet the user yourself, once, in a few words, with say, then call listen. action end hangs up (also happens when the user says "hang up" or "bye Claude", or after a long silence). During the call, speak with say and hear the user with listen.

NameTypeReqDescription
actionstringyesstart: take the mic (nothing is spoken); greet the user yourself, once, with say, then listen. end: hang up.

No output schema declared.

No examples provided.

flag ~91

Call only when the user explicitly asks to flag or report a bad voice turn; never on your own. Saves the last minute of what voice-mcp did (levels, why turns ended, whether speech finished: no transcripts) to a local file. Only works when the user turned the flight recorder on. Returns the file's path.

NameTypeReqDescription
notestring–Optional: what went wrong, in the user's words.

No output schema declared.

No examples provided.

listen ~110

During a call: return what the user has said since you last heard from them, at once if something is waiting, otherwise wait up to wait_seconds (default and maximum 40) for their next words. "(still on the call, nothing said)" means nobody spoke yet: call listen again to keep waiting, or say something. Once it reports that the call ended, don't call it again.

NameTypeReqDescription
wait_secondsnumber–How long to wait for the user to speak (default and maximum 40).

No output schema declared.

No examples provided.

say ~259

During a call: say text out loud and return at once, so you carry on working while it plays. The result includes anything the user said meanwhile. Only during a call: use speak_and_listen otherwise. Write text for the ear, not the screen: - 1–3 short sentences, under ~40 words; lead with the outcome, then one question. - Plain words only: no markdown, bullets, emoji, code, file paths, URLs, stack traces or tables. - Describe code instead of reading it ("I added a retry to the upload function"), say file names not paths ("in index.ts"), round numbers ("about two hundred ms"), spell out symbols. - Ask one question at a time, answerable in a few words ("Should I deploy it — yes or no?"). - Put the details (diffs, logs, links) in your normal on-screen reply, and say so out loud. - Tool output (Bash stdout, file writes) is NOT the on-screen reply. Only your own assistant message text renders. - A spoken turn with no assistant message text shows the user nothing — never skip the on-screen reply.

NameTypeReqDescription
textstringyesWhat to say. Plain, conversational text.

No output schema declared.

No examples provided.

speak_and_listen ~593

Say something out loud to the user and hear their spoken reply. Speaks text_to_speak through the computer's speakers, then listens like a conversation turn — it waits for the user to start talking and stops when they finish — and returns an on-device transcript of what they said. Write text_to_speak for the ear, not the screen: - 1–3 short sentences, under ~40 words; lead with the outcome, then one question. - Plain words only: no markdown, bullets, emoji, code, file paths, URLs, stack traces or tables. - Describe code instead of reading it ("I added a retry to the upload function"), say file names not paths ("in index.ts"), round numbers ("about two hundred ms"), spell out symbols. - Ask one question at a time, answerable in a few words ("Should I deploy it — yes or no?"). - Put the details (diffs, logs, links) in your normal on-screen reply, and say so out loud. - Tool output (Bash stdout, file writes) is NOT the on-screen reply. Only your own assistant message text renders. - A spoken turn with no assistant message text shows the user nothing — never skip the on-screen reply. Good: "The build passed and all tests are green. Want me to open the pull request?" Bad: "## Results\n- `npm test` ✅ 42/42\n- see /Users/x/repo/src/index.ts:120" Once the user is talking with you by voice, keep the conversation in voice: answer each transcript with another speak_and_listen call (not a text reply) until they say stop or start typing. To end voice mode, or for a one-way announcement, pass listen: false: it returns at once and speaks while you work. A reply of "(No speech detected …)" means the user did not answer — never treat it as consent. Ask once more; if still nothing, stop and say on screen that voice mode is paused and they can type to carry on (not speak: the mic is off). The "voice-mcp timing" line at the end is diagnostics: ignore it unless the user asks why things feel slow. If it reports that voice-mcp is not set up, call voice_setup.

NameTypeReqDescription
listenboolean–Default true. false: only speak, without opening the microphone — for a one-way announcement, or to say goodbye when the user ends voice mode. It returns right away and speaks while you carry on.
listen_secondsnumber–Upper limit on how long to listen, in seconds (default 30, max 120). Listening already stops when the user finishes talking, so you rarely need this.
text_to_speakstringyesThe summary or message to read aloud to the user. Plain, conversational text.

No output schema declared.

No examples provided.

voice_setup ~351

Check whether this computer has everything speak_and_listen needs — text-to-speech, a microphone recorder (SoX), whisper.cpp speech-to-text and the speech model — and optionally install what's missing. Anything already installed is reused (an existing model elsewhere on disk is symlinked, not re-downloaded). Call it with install=false (the default) first and tell the user what is missing. Only call it with install=true after the user agrees: it runs `brew install` for the missing packages and downloads the speech model once. It never uninstalls or changes anything else. kokoro=true (also only after the user agrees) installs the optional Kokoro voice: more natural than the built-in one, runs on this Mac, about 1 GB on disk. Once installed it's used automatically; the built-in voice stays as the fallback. bubble=true (also only after the user agrees) builds the floating call bubble on this Mac with swiftc: a small window during calls with mute and hang up. If it reports INSTALLING, the install continues in the background — wait a minute and call it again to check.

NameTypeReqDescription
bubbleboolean–true: build the floating call bubble on this Mac with swiftc (about 10 s; macOS). Ask the user first.
installboolean–false (default): only check. true: brew install missing packages and download the model. Ask the user first.
kokoroboolean–true: install the optional Kokoro voice — a natural-sounding neural voice that runs on this Mac (kokoro-js via npm and a one-time model download, about 1 GB on disk). Ask the user first.

No output schema declared.

No examples provided.

Install

How do I install the io.github.jeet0007/mac-voice-mcp server?

io.github.jeet0007/mac-voice-mcp runs locally as an npm package, launched with npx -y mac-voice-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · mac-voice-mcp

# add to Claude Code
claude mcp add jeet0007-mac-voice-mcp -- npx -y mac-voice-mcp
Common questions

What is the io.github.jeet0007/mac-voice-mcp server?

io.github.jeet0007/mac-voice-mcp is listed in the public MCP registry as io.github.jeet0007/mac-voice-mcp. Talk with your AI assistant out loud on a Mac, with on-device speech recognition (whisper.cpp). This page covers its npm package (mac-voice-mcp).

Is the io.github.jeet0007/mac-voice-mcp server safe to use?

io.github.jeet0007/mac-voice-mcp scores 96 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.jeet0007/mac-voice-mcp server expose?

io.github.jeet0007/mac-voice-mcp exposes 6 tools: speak_and_listen, call, say, listen, flag, voice_setup. Their descriptions and schemas cost roughly 1,563 tokens of context every time the server is loaded.

Is the io.github.jeet0007/mac-voice-mcp server still maintained?

io.github.jeet0007/mac-voice-mcp is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the io.github.jeet0007/mac-voice-mcp server under?

io.github.jeet0007/mac-voice-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the io.github.jeet0007/mac-voice-mcp server?

VerifyMCP ran 16 checks on io.github.jeet0007/mac-voice-mcp, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.