mocovoice

The mocoVoice MCP Server runs inside Docker and exposes a set of MCP commands that integrate Claude Desktop with the mocoVoice transcription service. It enables you to discover supported formats, list available files in a given workspace, start transcription jobs on specified audio/video files, and retrieve transcription results or statuses. The available commands are SHOW_USAGE, SHOW_AVAILABLE_FORMATS, SHOW_AVAILABLE_FILES, START_TRANSCRIPTION_JOB, SHOW_TRANSCRIPTION_RESULT, and CHECK_TRANSCRIPTION_STATUSES. To use it, configure Claude Desktop to run the Docker-based MCP server as shown in the Quickstart, providing the workspace directory path and your mocoVoice API key. When you start a transcription job, you must specify the absolute path to the file to ensure the server can access it. Copied results and job statuses can then be inspected via the MCP interface or returned results.

Prerequisites:

• Docker installed and running
• Claude Desktop installed and configured to use MCP servers
• A mocoVoice API key with READ/WRITE permissions

Installation steps:

1. Ensure Docker is running and you have network access to pull the image ghcr.io/mocomoco-inc/mocovoice-mcp-server
2. Create or edit the Claude Desktop MCP configuration file (claude_desktop_config.json) to include the mocoVoice MCP Server block, replacing <YOUR_DIR_PATH> with the absolute path to your audio/video workspace and <YOUR_API_KEY> with your mocoVoice API key:

{
  "mcpServers": {
    "mocoVoice MCP Server": {
      "command": "docker",
      "args": [
        "run",
        "--pull", "always",
        "-i",
        "--rm",
        "--mount", "type=bind,src=<YOUR_DIR_PATH>,dst=/workspace",
        "-e", "MOCOVOICE_API_KEY",
        "-e", "MOCOVOICE_API_URL",
        "ghcr.io/mocomoco-inc/mocovoice-mcp-server"
      ],
      "env": {
        "MOCOVOICE_API_KEY": "<YOUR_API_KEY>",
        "MOCOVOICE_API_URL": "https://api.mocomoco.ai/api/v1"
      }
    }
  }
}

3. Save the file and restart Claude Desktop or refresh the MCP configuration so the server is registered.
4. Verify connectivity by issuing the SHOW_USAGE command via the MCP interface to confirm the server is responsive.

Notes and tips:

• The container pulls the Mocovoice MCP Server image (ghcr.io/mocomoco-inc/mocovoice-mcp-server) and runs with the provided environment variables for API access.
• The workspace directory (<YOUR_DIR_PATH>) must be accessible to Docker and contain the audio/video files you intend to transcribe.
• The API key provided via MOCOVOICE_API_KEY must have appropriate permissions for transcription (READ/WRITE).
• Available file formats and maximum upload size are defined by the mocoVoice service; ensure you stay within those limits.
• If you encounter issues, check that Docker has permission to access the host filesystem and that the path mappings are correct.
• The server is currently described as a beta; features may be incomplete or subject to change.