Using AI/LLMs with the API

The Routable API 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 the Routable API and its documentation. If you are looking to use AI-powered development tools to get your implementation off the ground, empowering your development environment with this connectivity will make the generated code easier to produce and more reliable.

Additionally, we supply an LLMs.txt file to make it easier for AI tools to parse our 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 Routable API MCP server provides AI agents with:

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

Routable API MCP Server Setup

Routable API hosts a remote MCP server at https://developers.routable.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.

Add to~/.cursor/mcp.json:

{
  "mcpServers": {
    "routablehq": {
      "url": "https://developers.routable.com/mcp"
    }
  }
}

Testing Your MCP Setup

Once configured, you can test your MCP server connection:

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

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