io.github.decibri/mcp-listenmedia

mcp-listen

Verified · today

Give your AI agents the ability to listen. Microphone capture and speech-to-text.

Install

claude mcp add mcp-listen -- npx -y [email protected]

Our take

Microphone MCP server for listing audio devices, capturing WAV audio, and optionally running a local Whisper/Ollama voice-query pipeline. It is small but real, and the privacy story is good when used as documented because transcription and LLM calls can stay local. The optional voice path requires users to bring a Whisper GGML model and Ollama, so the zero-config part is mainly capture.

reviewed by hand · 2026-07-06

Something wrong or dead here? Report it

Verification record

last verified: today
github stars: 5
last commit: 16 days ago
archived: no
license: Apache-2.0
npm: mcp-listen
downloads / wk: 344
latest version: 0.1.3
in registry since: 2026-04-16

github.com/decibri/mcp-listen