What are the system requirements?
macOS with Pro Tools and PTSL enabled, Python 3.11+, and Claude Desktop are required.
@BlueElevatorProductions
基本情報
# protools-mcp
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": {
"protools-mcp": {
"command": "/path/to/protools-mcp/venv/bin/python",
"args": [
"/path/to/protools-mcp/server.py"
]
}
}
}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。
Pro Tools MCP is a local MCP server that connects Claude to a live Avid Pro Tools session via the PTSL (Pro Tools Scripting Library) gRPC API. It allows natural language conversation with the session—ask about the timeline, search transcripts, create markers, manage tracks, and execute session operations without leaving the chat. Built primarily for podcast post-production, it also works for music, broadcast, and audio post workflows.
To use Pro Tools MCP, you need macOS, Pro Tools with PTSL enabled, Python 3.11+, and Claude Desktop. After meeting these requirements, the server can be run locally to connect Claude to a live session. No additional configuration commands are provided in the README beyond the listed dependencies.
macOS with Pro Tools and PTSL enabled, Python 3.11+, and Claude Desktop are required.
Yes. While built for podcast post‑production, it works for music, broadcast, and audio post workflows.
It supports session snapshot, track list, markers, metadata, clip‑level details, time‑range queries, speech‑to‑text transcript search, playhead and selection navigation, creating markers, muting/soloing/unmuting tracks, selecting regions, saving, versioning, opening and closing sessions, and AAF export.
It is a per‑show configuration system for track assignments, host names, and naming conventions, useful for producers managing multiple shows.
It connects via the PTSL (Pro Tools Scripting Library) gRPC API, running locally on the same machine.

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
🚀 The fast, Pythonic way to build MCP servers and clients.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
不止于 CSS
コメント