AI agents that actually build your community.

1. Install Node.js (the LTS version) if you don't have it. Claude Desktop uses it to run the small HiveLearn connector on your computer.
2. In Claude Desktop, open Settings → Developer → Edit Config. This opens claude_desktop_config.json.
3. Paste the config below. If the file already has an mcpServers section, add the hivelearn entry inside it instead.
4. Save, then quit Claude Desktop completely (Cmd+Q on Mac, or right-click the tray icon and choose Quit on Windows). Reopen it.

{
  "mcpServers": {
    "hivelearn": {
      "command": "npx",
      "args": [
        "-y",
        "hivelearn-mcp"
      ],
      "env": {
        "HIVELEARN_API_KEY": "hl_live_YOUR_KEY_HERE"
      }
    }
  }
}

1. Run this once in your terminal. It makes HiveLearn available in every project.
2. Start Claude Code and type /mcp. HiveLearn should show as connected.

claude mcp add --transport http --scope user hivelearn https://mcp.hivelearn.app \
  --header "X-Hivelearn-Api-Key: hl_live_YOUR_KEY_HERE"

1. Open (or create) mcp.json in the .cursor folder in your home directory.
2. Paste the config below, or add the hivelearn entry to your existing mcpServers.
3. Save. HiveLearn shows a green dot in the MCP list when it connects.

{
  "mcpServers": {
    "hivelearn": {
      "url": "https://mcp.hivelearn.app",
      "headers": {
        "X-Hivelearn-Api-Key": "hl_live_YOUR_KEY_HERE"
      }
    }
  }
}

Any app that supports MCP over Streamable HTTP with custom headers can connect directly:

• Server URL: https://mcp.hivelearn.app
• Header: X-Hivelearn-Api-Key: hl_live_YOUR_KEY_HERE
• Or: Authorization: Bearer hl_live_YOUR_KEY_HERE

If the app can only start local servers, or can't send custom headers, use the same config as Claude Desktop. It runs npx -y hivelearn-mcp with your key in HIVELEARN_API_KEY.