jkawamoto/mcp-youtube-transcript

MCP server retrieving transcripts of YouTube videos

57
/ 100
Established

Exposes three tools via the Model Context Protocol: `get_transcript` and `get_timed_transcript` for retrieving video content with optional language selection, plus `get_video_info` for metadata. Implements automatic response pagination by splitting transcripts exceeding 50,000 characters with cursor-based retrieval to stay within LLM token limits. Integrates with Claude Desktop, Goose, and LM Studio through MCP, with Docker deployment support and configurable proxy handling for restricted networks.

337 stars.

No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

337

Forks

60

Language

Python

License

MIT

Last pushed

Feb 25, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/jkawamoto/mcp-youtube-transcript"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.