audio-mcp
by mshark1
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AUDIO_MCP_ROOT | No | Base directory for relative paths. | |
| AUDIO_MCP_FFMPEG | No | Path to the FFmpeg binary. With FFmpeg installed, the server can also read M4A/AAC, WMA, and audio from video files such as MP4, MOV, WebM and MKV. | |
| AUDIO_MCP_MAX_SECONDS | No | Largest section loaded into memory per call. Default is 1800. | 1800 |
| AUDIO_MCP_ALLOWED_DIRS | No | List of directories the server is allowed to read and write, separated by ';' on Windows and ':' elsewhere. By default, the server can read and write any file your user account can. | |
| AUDIO_MCP_WHISPER_MODEL | No | Whisper model used by audio_transcribe. Default is base. | base |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |