Skip to main content
The Lago MCP Server (Model Context Protocol) is written in Rust and provides AI assistants (like Claude) with direct access to Lago’s billing data. The server acts as a bridge between AI models and the Lago API, enabling natural language queries about invoices, customers, and billing information.

Lago MCP Server

​
Quick start using Claude Desktop

​
Configure Claude Desktop

The easiest way to get started is using the pre-built Docker image with Claude Desktop: 
{
  "mcpServers": {
    "lago": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "--name", "lago-mcp-server",
        "-e", "LAGO_API_KEY=your_lago_api_key",
        "-e", "LAGO_API_URL=https://api.getlago.com/api/v1",
        "getlago/lago-mcp-server:latest"
      ]
    }
  }
}

​
Set your credentials

Simply replace your LAGO_API_KEY with your actual Lago API key. You can find this in your Lago dashboard under API settings. Also, make sure that you are using the right LAGO_API_URL for your Lago instance.

​
Start chatting

Once configured, you can ask Claude natural language questions about your billing data:
  • “Show me all pending invoices from last month”
  • “Find all failed payment invoices”
  • “Give me the total amount of overdue invoices for the month of March 2025”
The list of available commands and their descriptions can be found in the Lago MCP Server GitHub repository. You can contribute to the project by adding more commands or improving existing ones.