MCP server for fetching YouTube transcripts
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"youtube-transcript-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# YouTube Transcript MCP Server [](https://pypi.org/project/youtube-transcript-mcp/) A Model Context Protocol server that allows you to download subtitles from YouTube and connect them to a LLM. This is just a thin wrapper on the youtube-transcript-api package. ## Features - Download transcripts of YouTube videos - Optionally include timestamps - Works with any MCP-compatible client ## Installation ### Option 1: Using uv (Recommended) Install [uv](https://github.com/astral-sh/uv) is a fast Python package installer and resolver. ```bash curl -LsSf https://astral.sh/uv/install.sh | sh ``` ### Option 2: Using pip If you prefer not to use uv, you can install using standard pip: ```bash pip install youtube-transcript-mcp ``` ## Usage ### In your MCP client configuration: #### If using uv: The `uvx` command is provided by uv and allows you to run Python packages directly: ```json "mcpServers": { "youtube": { "command": "uvx", "args": ["youtube-transcript-mcp"] }, } ``` #### If using standard Python: ```json "mcpServers": { "youtube": { "command": "python", "args": ["-m", "youtube_transcript_mcp"] }, } ``` ## License MIT
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.