MCP Servers

Connect AI applications and development tools to Taffrail through Model Context Protocol.

Taffrail offers two MCP servers — one for your applications to access Taffrail's rules engine, and one for your development tools to access our API documentation.

Taffrail MCP Server

The Taffrail MCP server provides AI agents with direct access to Taffrail's rules, tools, and data sources, enabling developers to build intelligent, context-aware AI experiences powered by Taffrail's Rules Engine.

Visit mcp.taffrail.com for configuration details and capabilities.

API Documentation MCP Server

The API Documentation MCP server gives AI-powered code editors (Cursor, Windsurf, Claude Desktop) access to Taffrail's OpenAPI spec and documentation, so your AI assistant can help you build integrations faster.

Server URL: https://docs.taffrail.io/mcp

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "taffrail": {
      "url": "https://docs.taffrail.io/mcp"
    }
  }
}

Testing Your Setup

Once configured:

  1. Open your AI editor (Cursor, Windsurf, etc.)
  2. Start a new chat with the AI assistant
  3. Ask about Taffrail — try questions like:
    • "How do I call the Taffrail Advice API?"
    • "Show me an example of using Taffrail's API"
    • "What parameters does the Advice endpoint accept?"

The AI assistant will have access to Taffrail's API documentation through the MCP server.