Whisper CLI

mcp server for whisper-cli

python

1

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "yhsung-whisper-cli-mcp": {
      "command": "python",
      "args": [
        "/path/to/whisper-cli-mcp/server.py"
      ]
    }
  }
}

You run a lightweight MCP server that exposes two practical capabilities: transcribing audio with OpenAI Whisper and safely executing shell commands. This server is easy to run locally and can be wired into an MCP client to automate transcription tasks or command execution in a controlled environment.

How to use

You connect to this server from an MCP client and invoke one of two available tools. Use whisper_transcribe to convert audio files into text using Whisper models of your choice. Use shell_command to run shell commands with built‑in safety checks that help prevent dangerous operations.

How to install

Prerequisites: you need Python installed on your system and access to install Python dependencies.

pip install -r requirements.txt

Make the server executable so you can run it directly.

chmod +x server.py

Run the server locally to start handling requests.

python server.py

Available tools

whisper_transcribe

Transcribe audio files using Whisper via the whisper-transcribe tool. You provide the audio_file path, optional model, language, and output_format to produce the transcription in your preferred format.

shell_command

Execute shell commands with basic security validation. You provide a command and an optional working_directory, and potentially receive the command output if it passes safety checks.