MCP

The Rillet 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 Rillet 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 Rillet MCP server provides AI agents with:

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

Rillet MCP Server Setup

Prerequisite: You'll need a Rillet API key.

Rillet hosts a remote MCP server at https://docs.api.rillet.com/mcp. Configure your AI development tools to connect to this server using bearer auth with your API key.

{
  "mcpServers": {
    "rillet-mcp": {
      "url": "https://docs.api.rillet.com/mcp",
      "headers": {
        "authorization": "Bearer <api key>"
      }
    }
  }
}

Environments

Rillet offers MCP access to both sandbox and production. We have two available environments:

You should instruct your AI agent which environment to use. For example, if you're testing in sandbox, you can say "Use the Rillet MCP in sandbox".

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. Instruct your AI assistant to use the Rillet MCP - try questions like:

• "Which endpoints are available?"
• "What customers do I have in Rillet?"
• "Do I have any overdue invoices?

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