mpv-mcp-server

by arijit-gogoi

179 downloads Not rated yet

About

An mcp for mpv cross platform media player.

Explore

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name mpv-mcp-server
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "mpv-mcp-server": {
            "server": {
                "command": "npx",
                "args": [
                    "-y",
                    "mpv-mcp-server"
                ],
                "env": {
                    "MPV_PATH": "",
                    "MPV_IPC_PATH": "",
                    "MPV_MEDIA_DIRS": "",
                    "MPV_DOWNLOAD_DIR": ""
                }
            }
        }
    }
}

McpServers

{
    "server": {
        "command": "npx",
        "args": [
            "-y",
            "mpv-mcp-server"
        ],
        "env": {
            "MPV_PATH": "",
            "MPV_IPC_PATH": "",
            "MPV_MEDIA_DIRS": "",
            "MPV_DOWNLOAD_DIR": ""
        }
    }
}

Transport

"stdio"

Package

"mpv-mcp-server"

Registry

"npm"

MCP server for controllingmpvmedia player. Browse your music library, control playback, stream from YouTube, and download tracks — all from inside an MCP client like Claude Code.

- mpv— media player (must be on your PATH, or setMPV_PATH)
-
Node.js22+
-
yt-dlp(optional)— required for YouTube streaming and downloading
-
ffmpeg(optional)— required for audio extraction, metadata reading (ffprobe), and tagging

{ "mcpServers": { "mpv": { "command": "npx", "args": ["-y", "mpv-mcp-server"] } } }

Or add at user scope (available in all projects):

claude mcp add mpv --scope user -- npx -y mpv-mcp-server
{ "mcpServers": { "mpv": { "command": "npx", "args": ["-y", "mpv-mcp-server"] } } }
{ "mcpServers": { "mpv": { "command": "npx", "args": ["-y", "mpv-mcp-server"], "env": { "MPV_PATH": "/usr/local/bin/mpv", "MPV_MEDIA_DIRS": "/home/user/Music,/home/user/Podcasts", "MPV_DOWNLOAD_DIR": "/home/user/Music" } } } }

All configuration is via environment variables. Everything has sensible defaults.

YouTube tools requireyt-dlpon your PATH. Audio downloads also requireffmpeg.

Both tools infer artist/title from the "Artist - Title" filename pattern. Requiresffmpeg(includes ffprobe).

The server communicates with mpv via itsJSON IPC protocol. On Windows this uses a named pipe, on macOS/Linux a Unix domain socket. If mpv isn't running, the server spawns it automatically in idle mode. The mpv process is detached, so it keeps playing even if the MCP server exits.

The World's First AI Music MCP Beyond images and video, your agent can now generate music.

Enables AI assistants to interact with DaVinci Resolve Studio for advanced control over video editing, color grading, and audio.

Transcribe and summarize video content from links using various transcription services.

: MCP server for AI media generation (imagesflux, videosveo3.1, music suno v5, with deterministic cost control using reserve-burn-refund billing

Create AI music videos and audio-reactive visuals from songs through MCP.

Turn any language model into a multimodal powerhouse that can generate images, music, videos and more on the fly. Rostro's tools are designed to be used by language models from the ground up, expanding capabilities with minimal context bloat.

All-in-one AI creative studio — generate videos, images, audio in 11 Indian languages, and 3D models via MCP. Hosted at mcp.arcframe.ai.

Official Cannon Studio MCP for AI video, image, 3D, audio, workflow, pricing, model, and developer API guidance.

A Python package for media processing using FFmpeg and FastMCP.

A server for creating fast and free lipsync videos for digital avatars, supporting both realistic and cartoon styles.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.