YouTube Captions
YouTube MCP Server provides tools for extracting and transforming YouTube video content, enabling AI assistants to fetch video metadata, captions in multiple languages, and convert transcripts to markdown with customizable templates. Built with TypeScript and the YouTube Data API, it supports both API key and OAuth2 authentication methods for accessing public and private videos. The server includes search functionality within captions, chapter extraction, and three built-in markdown templates (basic, detailed, and search), making it particularly useful for content analysis, research, and creating readable transcripts from video content.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- social-media
- Source
- PulseMCP
- Repository
- github.com/nattyraz/youtube-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve YouTube Captions from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp --scope user for --scope project to commit it to .mcp.json.