MCP

The Deliverect Model Context Protocol (MCP) server enables AI-powered code editors like Cursor and Windsurf, plus general-purpose tools like Claude Desktop, to interact directly with your Deliverect 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 Deliverect MCP server provides AI agents with:

• Documentation search capabilities
• Code generation assistance for Deliverect integrators

Deliverect MCP Server Setup

Deliverect hosts a remote MCP server at https://developers.deliverect.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.

Claude Desktop

Add the following to claude_desktop_config.json:

{
  "mcpServers": {
    "deliverect-api": {
      "url": "https://developers.deliverect.com/mcp"
    }
  }
}

Cursor

Add the following to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "deliverect-api": {
      "url": "https://developers.deliverect.com/mcp"
    }
  }
}

Windsurf

Add the following to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "deliverect-api": {
      "url": "https://developers.deliverect.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 Deliverect - try questions like:
   • "How do I process an order for Delivery?"
   • "Show me an example of a Menu payload"
   • "Create a full Commerce workflow using all available endpoints and webhooks"

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