広告掲載
MCP.so
ログイン

MIDI MCP Server

@tubone24

リポジトリ

基本情報

カテゴリ

その他

ライセンス

MIT

トランスポート

stdio

作者

tubone24

MIDI MCP Server について

MIDI MCP Server is a Model Context Protocol (MCP) server that enables AI models to generate MIDI files from text-based music data. This tool allows for programmatic creation of musical compositions through a standardized interface.

MIDI MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "midi-mcp-server": {
      "command": "node",
      "args": [
        "build/index.js",
        "--http"
      ]
    }
  }
}

MIDI MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is MIDI MCP Server?

A Model Context Protocol (MCP) server for AI-driven MIDI composition. It generates MIDI files from structured JSON data, supports chord names, provides an interactive piano-roll preview UI, and offers multiple deployment modes (stdio, HTTP, Cloudflare Workers).

How to use MIDI MCP Server?

Deploy remotely via Cloudflare Workers (https://midi-mcp-server.tubone24.workers.dev/mcp) or run locally as a stdio or HTTP server. Use the create_midi tool to generate a MIDI file from a composition object, and parse_chord to resolve chord names into pitches. See the README for configuration examples for each transport.

Key features of MIDI MCP Server

  • Two MCP tools: create_midi and parse_chord
  • Rich pitch input: MIDI numbers, note names, pitch arrays, or chord names
  • Chord library with 25+ chord qualities
  • Flexible durations: numeric beats, standard strings, dotted, triplet
  • Seven built-in music theory reference documents as MCP resources
  • Three transport modes: stdio, HTTP, Cloudflare Workers
  • Interactive piano-roll preview and audio playback in supported MCP clients

Use cases of MIDI MCP Server

  • Compose MIDI songs directly from an AI conversation
  • Parse chord names into MIDI pitches and note names for analysis
  • Use music theory resources to guide composition decisions
  • Generate multi-track MIDI files with specified instruments and velocities
  • Embed MIDI generation into MCP‑compatible clients (e.g., Claude.ai)

よくある質問

1

What deployment options are available?

The server can run as a local stdio process, a local HTTP server, or a remote Cloudflare Workers endpoint. The remote server is pre‑deployed at `https://midi-mcp-server.tubone24.workers.dev/mcp`.

2

What tools does the server expose?

Two tools: `create_midi` (generates a MIDI file from composition data) and `parse_chord` (resolves a chord name into its component MIDI numbers and note names).

3

What runtime and dependencies are required?

Node.js and npm. Key packages include `@modelcontextprotocol/sdk`, `midi-writer-js`, `zod`, and `soundfont-player`.

4

How do I specify pitches in a composition?

Pitches can be given as MIDI numbers (0–127), note name strings (e.g., `"C4"`), arrays of pitches, or chord names (e.g., `"Cmaj7"`). Accidentals `#` and `b` are supported.

5

What transport modes are supported?

The server supports stdio (default for local desktop clients), HTTP (local Streamable HTTP server), and Cloudflare Workers (remote, via HTTP). Authentication is not required.

コメント

「その他」の他のコンテンツ

Reactive Resume

amruthpillai

A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

39.5K

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Codelf

unbug

A search tool helps dev to solve the naming things problem.

14.2K
P

PickFu MCP

PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

FastMCP v2 🚀

jlowin

🚀 The fast, Pythonic way to build MCP servers and clients.

26.0K
広告掲載