YouTube DLP
This MCP server provides YouTube video analysis and content extraction using yt-dlp, enabling AI assistants to retrieve detailed video metadata, download subtitle content in multiple languages, and extract top comments sorted by engagement. Built by Robin with Python and featuring proxy support for restricted environments, it offers three core tools: video information extraction for metadata like title, duration, view counts, and available formats; subtitle and caption retrieval with automatic parsing and word count analysis for both manual and auto-generated captions; and top comment extraction with author identification, like counts, and special badges for creators and favorited comments. The implementation features asynchronous processing to avoid blocking, intelligent subtitle format detection and parsing, comprehensive language support with human-readable names, and detailed response formatting with previews and statistics, making it valuable for content analysis, research workflows, accessibility applications, and any use case requiring structured access to YouTube video data without manual browsing.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- social-media
- Source
- PulseMCP
- Author type
- human
- Updated
- 2026-07-22
Use via MCP
Resolve YouTube DLP 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.