tube-bridge for Cursor

io.github.thewhitewater/tube-bridge

YouTube MCP server for search, transcripts, frames, comments, channels, and local semantic corpora.

client:Cursor transport:stdio runtime:pypi

Install tube-bridge in Cursor

~/.cursor/mcp.json · windows: %USERPROFILE%\.cursor\mcp.json

{
  "mcpServers": {
    "tube-bridge": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "tube-bridge"
      ],
      "env": {
        "YOUTUBE_API_KEY": "<YOUTUBE_API_KEY>",
        "TUBE_BRIDGE_PROXY": "<TUBE_BRIDGE_PROXY>",
        "TUBE_BRIDGE_CACHE": "<TUBE_BRIDGE_CACHE>"
      }
    }
  }
}

Use .cursor/mcp.json in a project root instead to scope it to that project. Cursor merges both. Cursor docs

tube-bridge MCP server

Install tube-bridge in Cursor

tube-bridge in other clients