mcp-listenSAFE
Give your AI agents the ability to listen. Microphone capture and speech-to-text tools for MCP-compatible agents.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
<img src="https://github.com/user-attachments/assets/62a4c561-da48-401d-9142-220854566330" alt="Decibri mcp-listen" width="100%">
Give your AI agents the ability to listen
Microphone capture and speech-to-text tools for MCP-compatible agents.
Meta
Tools
Quick Start
Claude Code
claude mcp add mcp-listen npx mcp-listen
Claude Desktop / ChatGPT Desktop / Cursor / Windsurf / VS Code
Add to your MCP configuration:
{
"mcpServers": {
"mcp-listen": {
"command": "npx",
"args": ["-y", "cec76eb37862OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add mcp-listen -- npx -y [email protected]
Exposed tools (3)
3 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
capture_audio | read | Record audio from the microphone for a specified duration, or until the speaker stops talking with stop_on_silence, and save as a WAV file. Returns the file path and metadata. |
list_audio_devices | read | List available audio input devices (microphones) on this machine. Each device has a numeric index, a human-readable name, and a stable id. Prefer the id when selecting a device: indexes can shift when devices are added or removed, and names are not unique. |
voice_query | read | Record audio from the microphone, transcribe it on this machine with whisper.cpp, send the transcription to the local Ollama daemon, and return the transcription and the response. The audio stays on this machine. Recording stops automatically when the speaker stops talking. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
@modelcontextprotocol/sdk, decibri, @kutalia/whisper-node-addon, ollama
- Reads the `WHISPER_MODEL_PATH` environment variable to locate the local Whisper model. It reads no API credentials: none are used. The bundled Ollama client library can read `OLLAMA_API_KEY`, but it
Gates applied: no_behavioural_pass.
cec76eb37862full audit observations/trust-audit/mcp-server/decibri__mcp-listen.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | cec76eb37862 | SAFE | B | 89 | first audit |
Questions
What is the mcp-listen MCP server?
Give your AI agents the ability to listen. Microphone capture and speech-to-text tools for MCP-compatible agents.
What tools does mcp-listen expose?
3 in total: 3 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is mcp-listen safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does mcp-listen need?
No credential environment variables were found in its source, so it appears to need none.
How does mcp-listen run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as mcp-listen at 0.7.1.
How current is this page?
The grade is for one exact copy of the source (cec76eb37862), read on 2026-10-07. The repository is watched and re-audited when it changes.