Enables AI assistants to extract and analyze transcripts from public YouTube videos with caption support via Model Context Protocol integration for seamless use with Cursor and Claude Desktop.
Unlock the full potential of YouTube Transcript Extractor MCP through LangDB's AI Gateway. Get enterprise-grade security, analytics, and seamless integration with zero configuration.
Free tier available • No credit card required
A Model Context Protocol (MCP) server that enables AI assistants to extract transcripts from YouTube videos. Built for integration with Cursor and Claude Desktop, this tool allows AI to analyze and work with YouTube video content directly.
git clone https://github.com/yourusername/yt-mcp.git cd yt-mcp
pnpm install
pnpm run build
youtube-transcript
command
node /absolute/path/to/yt-mcp/build/index.js
Add this configuration to your Claude Desktop config:
{ "mcpServers": { "youtube-transcript": { "command": "node", "args": ["/absolute/path/to/yt-mcp/build/index.js"] } } }
Once configured, the AI can extract transcripts from YouTube videos by calling the tool with a video URL. Example:
// The AI will use this format internally const transcript = await extractTranscript({ input: "https://www.youtube.com/watch?v=VIDEO_ID" });
The server is built using:
Common issues and solutions:
"Cannot find video ID" error
"No transcript available" error
Build errors
Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.
MIT
Discover shared experiences
Shared threads will appear here, showcasing real-world applications and insights from the community. Check back soon for updates!