MCP

The Pinwheel Model Context Protocol (MCP) server enables AI-powered code editors like Cursor and general-purpose tools like Claude Desktop, to interact directly with your Pinwheel API and documentation.

What is MCP?

Model Context Protocol (MCP) is an open standard that allows AI applications to securely access external data sources and tools. The Pinwheel MCP server provides AI agents with:

• Direct API access to Pinwheel functionality
• Documentation search capabilities
• Real-time data from your Pinwheel account
• Code generation assistance for Pinwheel integrations

Pinwheel MCP Server Setup

Pinwheel hosts a remote MCP server at https://docs.pinwheelapi.com/mcp. Configure your AI development tools to connect to this server. If your APIs require authentication, you can pass in headers via query parameters or however headers are configured in your MCP client.

{
  "mcpServers": {
    "pinwheelapi": {
      "url": "https://docs.pinwheelapi.com/mcp"
    }
  }
}

{
  "mcpServers": {
    "pinwheelapi": {
      "url": "https://docs.pinwheelapi.com/mcp"
    }
  }
}

Testing Your MCP Setup

Once configured, you can test your MCP server connection:

1. Open your AI editor (Cursor, Windsurf, etc.)
2. Start a new chat with the AI assistant
3. Ask about Pinwheel - try questions like:
   • "How do I [common use case]?"
   • "Show me an example of [API functionality]"
   • "Create a [integration type] using Pinwheel"

The AI should now have access to your Pinwheel account data and documentation through the MCP server.