mcpField
M
musescore-mcp

musescore-mcp

Local
github.com/chrischallGames & Entertainment
Repository

About musescore-mcp

MuseScore for Claude — search sheet music and read score metadata via your signed-in browser

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "chrischall-musescore": {
      "command": "npx",
      "args": [
        "-y",
        "@chrischall/musescore-mcp"
      ],
      "env": {
        "MUSESCORE_WS_PORT": "<MUSESCORE_WS_PORT>",
        "MUSESCORE_OUTPUT_DIR": "<MUSESCORE_OUTPUT_DIR>"
      }
    }
  }
}
Run commandnpx -y @chrischall/musescore-mcp
Environment variables to set
MUSESCORE_WS_PORTOverride the fetchproxy WebSocket port (default 37149).
MUSESCORE_OUTPUT_DIRDirectory every file-writing tool is confined to (default ~/Downloads): an output_path/output_dir outside it is refused, a relative path is resolved against it, and musescore_svg_to_pdf only reads svg_paths from inside it.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@chrischall/musescore-mcp1.2.0

Tools

10

Saved tool list · updated 1w ago

ParameterTypeRequiredDescription
pageintegerNo1-based result page. Defaults to 1.
querystringYesFree-text search query.
free_onlybooleanNoRestrict to the "Free to view, play & download" facet. Defaults to true.
complexityenumNoDifficulty facet.beginner | intermediate | advanced
instrumentstringNoInstrument facet: a supported instrument name (e.g. piano, guitar, violin, flute, trombone, baritone, tuba, organ, bassoon, saxophone alto, euphonium, cornet, accordion, soprano, alto, voice), or a MuseScore numeric instrument id (e.g. 2=piano, 72=guitar, 4=trombone). Unrecognized names error — pass the numeric id instead.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.