YouTube Insights MCP Server
Extract insights from YouTube videos, including subtitles, video discovery, and channel information.
YouTube Insights MCP Server
A Model Context Protocol (MCP) server that enables insight extraction from YouTube videos, including subtitle parsing, keyword-based video discovery, and channel info retrieval.
Features
- Extract transcripts from YouTube videos (multi-language)
- Search videos by keyword and fetch metadata (views, likes, thumbnails, etc.)
- Retrieve channel info and latest videos from any YouTube video URL
- FastMCP-based server integration for easy deployment
- MCP Tools for seamless agent workflows
Example usecases
Finding Trending Videos and Summarizing
Analyzing a Channel's Recent Performance
Installation
Installing via Smithery
To install youtubeinsights-mcp-server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @dabidstudio/youtubeinsights-mcp-server --client claude
Using uvx (recommended)
When using uvx, no specific installation is needed.
Add the following configuration to your MCP settings file (e.g., claude_desktop_config.json for Claude Desktop):
{
"mcpServers": {
"youtubeinsights": {
"command": "uvx",
"args": ["youtubeinsights-mcp-server"],
"env": {
"YOUTUBE_API_KEY": "your-api-key",
}
}
}
}
Development Installation
-
Clone this repository
-
Copy
.env.exampleto.envand fill in your youtube data api credentials{ "mcpServers": { "youtubeinsights": { "command": "uv", "args": [ "--directory", "path/to/youtubeinsights-mcp-server", "run", "youtubeinsights-mcp-server" ], "env": { "YOUTUBE_API_KEY": "your-api-key", } } } }
Available MCP Tools
get_youtube_transcript: Extract full transcript (subtitles) from a YouTube video URL (supportsko,en)search_youtube_videos: Search for videos on YouTube by keyword and retrieve key metadataget_channel_info: Get channel metadata and recent uploads based on any YouTube video URL
Sample MCP Tool Descriptions
{
"tool": "get_youtube_transcript",
"description": "Extract subtitles from a given YouTube video URL."
}
{
"tool": "search_youtube_videos",
"description": "Search videos by keyword and return metadata including views, likes, and thumbnails."
}
{
"tool": "get_channel_info",
"description": "Retrieve channel info (title, subscriber count, latest uploads) based on a video URL."
}
License
This project is licensed under the MIT License. See the LICENSE file for details.
Máy chủ liên quan
Bright Data
nhà tài trợDiscover, extract, and interact with the web - one interface powering automated access across the public internet.
AgentQL
Enable AI agents to get structured data from unstructured web with AgentQL.
Leapfrog
Multi-session browser MCP for AI agents — stealth mode, session pooling, humanization, 10x fewer tokens than Playwright
Financial Data MCP Server
Provides real-time financial market data from Yahoo Finance.
deadlink-checker-mcp
Dead link checker MCP server - find broken links, redirects, and timeouts on any website.
MCP LLMS.txt Explorer
Explore and analyze websites that have implemented the llms.txt standard.
CrawlAPI
Scrape any URL with JavaScript rendering and get back clean markdown — built for AI agents, LLM pipelines, and autonomous research workflows.
BrowserAct
BrowserAct MCP Server is a standardized MCP service that lets MCP clients connect to the BrowserAct platform to discover and run browser automation workflows, access results/files and related storage, and trigger real-world actions via natural language.
HTTP Requests
An MCP server for making HTTP requests, enabling LLMs to fetch and process web content.
Unchained Sky
Browser automation MCP server that connects AI agents to your real Chrome browser with structured page understanding in ~500 tokens
Deepwiki
Fetches content from deepwiki.com and converts it into LLM-readable markdown.