contextLines
surrounding segments to retain, from 0 to 5
How to use it
contextLines is exposed by the Youtube MCP Server MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the contextLines tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Youtube MCP Server
npx @modelcontextprotocol/inspectorOther tools in Youtube MCP Server (21)
Analyze performance trends of videos from a specific channel
Compare statistics across multiple videos
Advanced transcript extraction with filtering, search, and multi-video capabilities
Get subscriber count, view count, and other channel statistics
Extract key moments with timestamps from a video transcript for easier navigation
Divide a video transcript into segments for easier analysis
Retrieve trending videos by region and category
Get available video categories for a specific region
Get comments for a specific video
Get statistical information for a specific video
Get transcript for a specific video with optional language
optional caption language such as en, ko, or ja
word (default) or substring
response cap from 1 to 1,000 (default: 200)
result offset for pagination
optional phrase to find inside the transcript
Get citation-ready transcript evidence from a URL or video ID without an API key
Compare timestamp-linked evidence across 2–5 videos without an API key
Search for YouTube videos with advanced filtering options
/ endSeconds: optional time window
a YouTube URL or 11-character video ID