Listen MCP Server

Give your AI agents the ability to listen Microphone capture and speech-to-text tools for MCP-compatible agents. Its 3 documented tools cluster into read & search, capture, voice. It runs locally over stdio via the published package.

People connecting media tools to Claude, Cursor, VS Code, or another MCP client. The project is written in JavaScript.

VERIFIED ACTIVE

LAST COMMIT 2026-08-12 · ★ 8 · #74 OF 155 MAINTAINED MEDIA · VERIFIED 2026-08-25

Apache-2.0 · JavaScript servers · how we verify → /methodology

01 · Install Listen

Claude Code

claude mcp add analyticsinmotion-mcp-listen -- npx -y mcp-listen

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "analyticsinmotion-mcp-listen": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-listen"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license Apache-2.0 - declared in the repository

npm package mcp-listen - unscoped; check the name against the project README before installing

registry namespace io.github.analyticsinmotion is GitHub-verified and matches the repo owner

03 · What Listen can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can list available microphone input devices, and capture, transcribe (whisper.cpp), and query a local LLM (Ollama).

The 3 tools it gives your agent

Extracted from the project's README - what mcp-listen lets an agent do.

list_audio_devices
- List available microphone input devices
capture_audio
- Record audio from the microphone and save as WAV
voice_query
- Capture, transcribe (whisper.cpp), and query a local LLM (Ollama)

Latest releases

v0.6.0 · 2026-07-15

condition voice_query audio for transcription · v0.6.0

v0.5.0 · 2026-07-15

publish the MCP registry entry from the release workflow · add a contribution guide · Add Contributor Covenant Code of Conduct · stop recording when the speaker stops talking

v0.4.0 · 2026-07-14

misleading load errors, temp file buildup, leaky publish manifest

04 · Who maintains Listen

mcp-listen is maintained by analyticsinmotion. It's the only MCP server we track from this author; the repo dates to Apr 2026.

05 · Facts

category
media - ranked #74 of 155 actively-maintained media servers as of 2026-08-25.
release cadence
6 releases in the last 90 days (latest 2026-07-15)
registry
io.github.analyticsinmotion/mcp-listen (active, first published 2026-04-05)
packages
npm:mcp-listen

06 · Listen FAQ

Is Listen still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-12 and it shipped 6 releases in the last 90 days. We re-verify nightly.

What can Listen do?

With this server connected, an agent can list available microphone input devices, and capture, transcribe (whisper.cpp), and query a local LLM (Ollama).

How do I install Listen?

Run `npx -y mcp-listen`. You can also paste the ready-made client config above.

Does Listen run locally?

Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Listen