Overview
What is YouTube Insights MCP Server?
YouTube Insights MCP Server is an MCP server that extracts insights from YouTube videos, including subtitle parsing in multiple languages, keyword-based video discovery, and channel information retrieval. It is designed for use with AI agents and MCP-compatible clients like Claude Desktop.
How to use YouTube Insights MCP Server?
Install automatically via Smithery or manually with uvx. Add the server configuration (e.g., in claude_desktop_config.json) with the YOUTUBE_API_KEY environment variable set to your YouTube Data API key. The server provides three tools: get_youtube_transcript, search_youtube_videos, and get_channel_info.
Key features of YouTube Insights MCP Server
- Extract transcripts from YouTube videos (multi-language)
- Search videos by keyword and fetch metadata (views, likes, thumbnails)
- Retrieve channel info and latest uploads from any video URL
- FastMCP-based server for easy deployment
- MCP Tools for seamless agent workflows
Use cases of YouTube Insights MCP Server
- Analyze a channel’s recent performance and subscriber growth
- Summarize trending or specific videos from search results
- Extract and analyze subtitles from videos in Korean or English
FAQ from YouTube Insights MCP Server
What API key is required?
You need a YouTube Data API key. Set it as the environment variable YOUTUBE_API_KEY in the MCP server configuration.
What languages are supported for transcripts?
The get_youtube_transcript tool currently supports Korean (ko) and English (en) subtitles.
What MCP tools are available?
Three tools: get_youtube_transcript (extract subtitles), search_youtube_videos (search by keyword and return metadata), and get_channel_info (retrieve channel data and recent uploads from a video URL).
How do I install the server?
You can install via Smithery (npx -y @smithery/cli install @dabidstudio/youtubeinsights-mcp-server --client claude) or use uvx with the configuration shown in the README.