
Mcp Listen
Adds three microphone tools to your MCP client: list available audio devices, capture audio to WAV files, and run a full offline voice pipeline. The voice_query tool chains capture, whisper.cpp transcription, and local Ollama inference so you can speak questions and get LLM responses without any cloud services. Built on decibri for cross-platform audio capture with no external dependencies like ffmpeg. You specify recording duration upfront since there's no voice activity detection yet. Works with Claude Desktop, Cursor, and other MCP clients. Useful when you want voice input without API calls or when building offline voice workflows.
- GitHub stars
- 10
- tools
- 3
- transport
- STDIO
- last updated
- Oct 13, 2026
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
list_audio_devicesList available microphone input devices
List available microphone input devices
No parameter schema in public metadata yet.
capture_audioRecord audio from the microphone and save as WAV
Record audio from the microphone and save as WAV
No parameter schema in public metadata yet.
voice_queryCapture, transcribe on this machine (whisper.cpp), and query a model through the local Ollama daemon
Capture, transcribe on this machine (whisper.cpp), and query a model through the local Ollama daemon
No parameter schema in public metadata yet.
Sponsors
Readme
Details
- Repository
- github.com/decibri/mcp-listen
- Category
- Media & Entertainment
- Package
mcp-listen- Transport
- STDIO
- Registry
- MCP registry, active