This MCP server provides a production-grade interface to the YouTube Data API, optimized for AI agents by reducing payload size and protecting API quotas through caching.
From the registry: YouTube MCP server for token-optimized, structured data using the YouTube Data API v3.
Please install the `mcp-youtube` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js 20+** — Node.js version 20 or higher
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@kirbah/mcp-youtube"]
- optional environment variables:
- `YOUTUBE_API_KEY`: YouTube Data API v3 key. Omit for zero-config transcript-only mode. (example: `<your-api-key>`)
- `MDB_MCP_CONNECTION_STRING`: MongoDB connection string for optional caching/outlier channel analysis (example: `<your-mongodb-uri>`)
Note: Works in zero-config mode without API key (transcripts only). Add YOUTUBE_API_KEY to unlock all features.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.YOUTUBE_API_KEYrequiredAPI key for accessing the YouTube Data API v3.MDB_MCP_CONNECTION_STRINGMongoDB connection string for enabling caching.MCP server for searching Airweave collections with natural language queries.