API Keys and MCP Configuration

Zhu Li provides a Model Context Protocol (MCP) server that lets you connect AI-powered code editors like Claude Desktop, Cursor, and Claude Code directly to your workspace.

Step 1: Get your API Key

Your API key is required to authenticate your MCP client with the Zhu Li server.

1. Go to your Zhu Li dashboard → Settings.
2. Under the API Key section, you will see your current masked key.
3. Click Rotate API Key if you need a new one (copy it immediately as it's only shown once).

Step 2: Configure Claude Desktop

To connect Claude Desktop to Zhu Li, you need to add the server configuration to your mcp.json file.

1. Locate your mcp.json file:
   • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%\Claude\claude_desktop_config.json
2. Add the zhu-li configuration to the mcpServers object:

{
  "mcpServers": {
    "zhu-li": {
      "url": "https://zhuli.aevr.space/api/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

3. Replace YOUR_API_KEY with the key you obtained in Step 1.
4. Restart Claude Desktop.

Step 3: Configure Cursor

Cursor supports MCP servers via its settings menu.

1. Open Cursor and go to Settings → Features → MCP.
2. Click + Add New MCP Server.
3. Set the Name to zhu-li.
4. Set the Type to command (if using a local CLI) or sse (if using the remote URL).
5. For the URL, use: https://zhuli.aevr.space/api/mcp.
6. Add an Authorization header with the value Bearer YOUR_API_KEY.

What can you do with Zhu Li MCP?

Connecting your editor to Zhu Li allows your AI coding assistant to:

• Search Notion: Query your workspace for existing issues, PRDs, and documentation.
• Submit Issues: Found a bug? Let the AI submit it directly to Notion without leaving the editor.
• Contextual Awareness: The AI can link the code it's writing to the specific feature or bug report you're working on.