foo_ai
AI MCP control for foobar2000. Control your music player with an AI assistant!
claude mcp add --transport stdio bobini1-foo_ai node path/to/server.js \ --env MCPC_HOST="localhost" \ --env MCPC_PORT="9910" \ --env MCPC_SSE_PATH="/sse"
How to use
foo_ai exposes a local Model Context Protocol (MCP) server to control foobar2000 via an AI assistant. The server runs locally and can be connected to by any MCP client that supports Server-Sent Events (SSE). Once connected, you can issue natural language tasks to the assistant, which will translate them into MCP tool calls. Typical tasks include listing and managing foobar2000 playlists, querying the current track, adjusting volume, and initiating playback. The available tools cover library inspection (list_library, list_playlists, list_playlist, list_current_track), playlist management (create_playlist, delete_playlist, rename_playlist, add_tracks, remove_tracks, move_tracks, set_active_playlist, set_playing_playlist), playback control (set_playback_state, play_at_index, set_focus), and volume control (set_volume, toggle_mute, get_volume). The server also exposes real-time resources like current_track, playlists, and volume to subscriptions, which can be useful for clients that support live updates.
How to install
Prerequisites:
- A compatible MCP client that supports SSE.
- Access to install the foo_ai server (as described in the project releases).
- Network access to localhost where the MCP server will run (default port 9910).
Installation steps:
- Download the latest release of foo_ai from the Releases page on GitHub.
- Extract or install the component as instructed by the release (the README mentions installing the foobar2000 component; follow those steps if applicable).
- Ensure the MCP server is running. By default, the server listens on http://localhost:9910/sse; you can change the host and port in the server settings if needed.
- In your MCP client, add the server URL (for example http://localhost:9910/sse) to establish a connection and start issuing commands.
- Save settings and test a simple query, such as asking for the current track or listing your playlists, to confirm the connection.
Notes:
- If you run into port conflicts, change the MCPC_HOST/MCPC_PORT values in the environment or server configuration and update your client accordingly.
Additional notes
Tips and considerations:
- The server supports a range of tools for library, playlist, playback, and volume management. Familiarize yourself with the tool names to craft precise requests.
- For real-time updates, you can subscribe to resources like current_track, playlists, and volume, though polling the tools is always an option if subscriptions are not supported by your client.
- If you see connection errors, verify the server address and port, ensure the MCP client supports SSE, and confirm any firewall rules allow local network traffic to the specified port.
- You can adjust the listening host/port in settings (default: http://localhost:9910/sse). Ensure your MCP client points to the updated URL.
- When upgrading to new releases, re-check the toolset as new tools or resources may be added or existing ones updated.
Related MCP Servers
Wax
Sub-Millisecond RAG on Apple Silicon. No Server. No API. One File. Pure Swift
Unreal_mcp
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to control Unreal Engine through the native C++ Automation Bridge plugin. Built with TypeScript, C++, and Rust (WebAssembly) for ultra-high-performance game development automation.
furi
CLI & API for MCP management
openfoam
LLM-powered OpenFOAM MCP server for intelligent CFD education with Socratic questioning and expert error resolution
flapi
API Framework heavily relying on the power of DuckDB and DuckDB extensions. Ready to build performant and cost-efficient APIs on top of BigQuery or Snowflake for AI Agents and Data Apps
processhacker
your ai debugger, vibe hacking tool