YouTube Knowledge

Query YouTube via MCP to search, fetch details, analyze transcripts and comments, and power AI workflows.

typescript

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "efikuta-youtube-knowledge-mcp": {
      "command": "node",
      "args": [
        "/absolute/path/to/youtube-knowledge-mcp/build/index.js"
      ],
      "env": {
        "LOG_LEVEL": "info",
        "REDIS_URL": "redis://localhost:6379",
        "REDIS_HOST": "localhost",
        "REDIS_PORT": "6379",
        "OPENAI_API_KEY": "optional_openai",
        "REDIS_PASSWORD": "password",
        "MAX_DAILY_QUOTA": "8000",
        "YOUTUBE_API_KEY": "your_youtube_api_key",
        "ANTHROPIC_API_KEY": "optional_anthropic"
      }
    }
  }
}

YouTube Knowledge MCP is a production-ready MCP server that turns YouTube into a queryable knowledge source. It lets you search videos, fetch details, analyze transcripts and comments, and power AI-driven workflows with optional AI providers. It’s designed to be fast, quota-aware, and easy to connect with MCP clients like Claude Desktop.

How to use

You can use this MCP server from an MCP client to perform targeted queries against YouTube data. Start by running the MCP locally or remotely, then connect your client with the provided configuration. Once connected, you can search for videos, fetch video details and transcripts, analyze content with AI tools, and generate insights such as topics, summaries, chapters, and knowledge graphs. If you enable AI providers, you gain enhanced capabilities like topic extraction, sentiment analysis, and learning-path generation.

How to install

Prerequisites you need before installation:

Node.js 18+
YouTube Data API v3 key (required)

Step-by-step setup and run flow:

Install dependencies
Configure environment variables
Run the server in development or production mode
Connect your MCP client with the provided config

Available tools

youtube_search

Search videos with filters such as term, duration, date, and more.

get_video_details

Fetch video metadata, transcript (best-effort), and comments.

get_trending_videos

Retrieve most popular videos by region or category.

search_channels

Search channels with optional statistics and details.

analyze_video_content

AI-driven topics, sentiment, questions, summary, and keywords from video content.

generate_learning_path

AI-generated learning path for a given topic.

analyze_comment_intents

Classify viewer intents from comments.

simplify_video_transcript

ELI5-style simplification of transcripts.

generate_video_chapters

AI-generated chapters with timestamps.

generate_knowledge_graph

Cross-video concept graph showing relationships between ideas.

Built by

VeilStrat

AI signals for GTM teams