FunASR MCP
v0.1.2io.github.modelscope/funasr-mcp
Transcribe local audio with FunASR and SenseVoice using private, on-device inference.
transport:stdio
runtime:oci
Target client
run in your project directory
claude mcp add funasr-mcp -- docker run -i --rm ghcr.io/modelscope/funasr-mcp:0.1.2
Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs
This listing does not declare its tools. Connect the server and your client will discover them on the handshake.