Token Optimized Youtube Data and Transcript
@kirbah
Token Optimized Youtube Data and Transcript について
High-efficiency YouTube MCP server: Get token-optimized, structured data for your LLMs using the YouTube Data API v3.
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"youtube": {
"command": "npx",
"args": [
"-y",
"@kirbah/mcp-youtube"
],
"env": {
"YOUTUBE_API_KEY": "YOUR_YOUTUBE_API_KEY_HERE",
"MDB_MCP_CONNECTION_STRING": "optional db for cache ie. mongodb+srv://user... server.com"
}
}
}
}ツール
9Retrieves detailed, **lean** information for multiple YouTube videos including metadata, statistics, engagement ratios, and content details.
Searches for videos or channels based on a query string with various filtering options, returning **concise** results.
Retrieves **token-efficient** transcripts (captions) for multiple videos, with options for full text or key segments (intro/outro).
Retrieves **lean** statistics for multiple channels (subscriber count, view count, video count, creation date).
Retrieves a list of a channel's top-performing videos with **lean** details and engagement ratios.
Retrieves a list of trending videos for a given region and optional category, with **lean** details and engagement ratios.
Retrieves available YouTube video categories (ID and title) for a specific region, providing **essential data only**.
Retrieves comments for a YouTube video. Allows sorting, limiting results, and fetching a small number of replies per comment.
Identifies channels that consistently perform as outliers within a specific niche. **Requires a MongoDB connection.**
概要
What is Token Optimized Youtube Data and Transcript?
Token Optimized Youtube Data and Transcript is a production-grade MCP server designed for AI agents to interact with YouTube data efficiently. It strips redundant payload from YouTube API responses to save context window tokens and includes optional MongoDB caching to protect API quotas. It supports zero-config mode for transcript fetching without an API key, and full video search, channel analytics, trending, and comment retrieval with a YouTube Data API v3 key.
How to use Token Optimized Youtube Data and Transcript?
Install via npx with npx -y @kirbah/mcp-youtube in your MCP client configuration. For full features, set the YOUTUBE_API_KEY environment variable and optionally MDB_MCP_CONNECTION_STRING for caching. The server provides tools like getVideoDetails, searchVideos, getTranscripts, getChannelStatistics, getTrendingVideos, and getVideoComments. Use zero-config mode by just adding the base npx command; transcripts work immediately without any API key.
Key features of Token Optimized Youtube Data and Transcript
- Token‑efficient data structure saving up to 87% of LLM context tokens.
- Optional MongoDB caching layer to avoid duplicate API quota consumption.
- Multi‑language transcript retrieval with full text or key segments.
- 97% test coverage, zero lint errors, and active Dependabot security patching.
- Tools for video details, search, channel stats, trending, categories, and comments.
- Zero‑config mode for transcripts; no API key required.
Use cases of Token Optimized Youtube Data and Transcript
- Content summarization and analysis from video transcripts.
- Market research and trend tracking by region and category.
- Sentiment analysis and feedback extraction from video comments.
- Niche outlier detection using channel performance metrics (requires MongoDB).
- Building cost‑effective AI workflows with strict YouTube API quota limits.
FAQ from Token Optimized Youtube Data and Transcript
Do I need a YouTube API key to use this server?
No, you can use zero‑config mode to fetch transcripts without any API key. For video search, channel stats, trending, and comments you need a YouTube Data API v3 key set as the YOUTUBE_API_KEY environment variable.
How does the caching layer protect my API quota?
An optional MongoDB connection string (MDB_MCP_CONNECTION_STRING) enables a cache. If your agent requests the same data twice, the server returns the cached result, costing zero API quota units.
What are the runtime dependencies?
Node.js version 20.0.0 or higher and npm. For local development, clone the repository and run npm ci.
What is the API quota cost for each tool?
Most tools cost 1 unit per call (e.g., getVideoDetails, getChannelStatistics). getTranscripts costs 0 units. Search tools like searchVideos cost 100 units, and getVideoComments has a variable cost: 1 unit base plus 1 unit per top‑level comment if replies are requested.
How does authentication work?
Authentication is handled via the YOUTUBE_API_KEY environment variable.
「メディアとデザイン」の他のコンテンツ
BibiGPT AI video & audio summarizer
JimmyLvOpenClaw / Claude Code / Codex Agent skill for summarizing videos/audio via BibiGPT CLI (bibi)
Video Editor MCP server
burningionMCP Interface for Video Jungle
Photoshop MCP Server
loonghaoA Model Context Protocol (MCP) server that interfaces with Adobe Photoshop's Python API. Enables LLMs to execute image editing operations, automate workflows, and manage Photoshop tasks through structured commands and context-aware interactions.
MiniMax MCP JS
MiniMax-AIOfficial MiniMax Model Context Protocol (MCP) JavaScript implementation that provides seamless integration with MiniMax's powerful AI capabilities including image generation, video generation, text-to-speech, and voice cloning APIs.
Figma MCP Server
TimHoldenModel Context Protocol server implementation for Figma API
コメント