youtube-transcript-mcp

Transcribe YouTube videos for LLM chat apps via MCP.

Example prompt: Summarize https://www.youtube.com/watch?v=uB9yZenVLzg

Install

Requires uv. Add this to your MCP client's config — works for any MCP-compatible app (Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, Zed, …):

{
  "mcpServers": {
    "youtube-transcript": {
      "command": "uvx",
      "args": ["youtube-transcript-mcp-server"]
    }
  }
}

Equivalent one-liner if your client wants a single command:

uvx youtube-transcript-mcp-server

That's it — uvx fetches the package from PyPI on first run and caches it. Restart the client after editing its config.

Tool

• transcribe(youtube_video_url: str) -> str — fetches the transcript (en/de/es/fr/ru) and prepends an ad-removal instruction for the LLM.

Develop locally

git clone https://github.com/SeanPedersen/youtube-transcript-mcp
cd youtube-transcript-mcp
uv venv && uv pip install -r pyproject.toml && source .venv/bin/activate
python mcp_server.py

Point your MCP client at the local checkout instead of PyPI:

{
  "command": "uv",
  "args": [
    "run", "--with", "fastmcp", "--with", "youtube-transcript-api",
    "fastmcp", "run", "/absolute/path/to/youtube-transcript-mcp/mcp_server.py"
  ]
}

Release

1. Bump version in pyproject.toml.
2. Copy .env.example to .env and add your PyPI token.
3. ./scripts/release.sh — builds and publishes to PyPI.