Skip to main content

DX MCP Server

The DX MCP Server is a Model Context Protocol (MCP) server that empowers AI assistants with deep knowledge of PagoPA's DX ecosystem. It bridges the gap between AI-powered development tools and PagoPA's technical documentation, best practices, and code repositories.

What is the Model Context Protocol?​

The Model Context Protocol (MCP) is an open standard that enables AI assistants to interact with external tools and data sources in a structured way. MCP-compliant clients (like GitHub Copilot, Claude Desktop, or VS Code) can connect to MCP servers to access specialized knowledge and capabilities.

How It Works​

The DX MCP Server provides AI assistants with access to:

  1. PagoPA DX Documentation: Query the complete DX technical documentation using natural language
  2. REST Knowledge Endpoints: Access the same knowledge base through /ask and /search for direct HTTP integrations

Getting Started​

Configuration​

VS Code / GitHub Copilot​

Install in VS Code

After installing the MCP server in VS Code, update your MCP configuration file as follows:

{
  "servers": {
    "dx": {
      "url": "https://api.dx.pagopa.it/mcp",
      "type": "http"
    }
  }
}

See VS Code MCP docs for more info.

GitHub Copilot Coding Agent​

Configure in your repository settings under "Copilot" >> "Coding agent". See GitHub Copilot MCP docs for more info.

{
  "mcpServers": {
    "pagopa-dx": {
      "url": "https://api.dx.pagopa.it/mcp",
      "type": "http",
      "tools": ["*"]
    }
  }
}

GitHub Copilot CLI​

To use the MCP server with GitHub Copilot CLI, run the cli with copilot and prompt /mcp add to start the configuration of the MCP server

Follow the guided wizard to start using the DX MCP server:

  1. Server Name:
pagopa-dx
  1. Server Type: HTTP
  2. URL:
https://api.dx.pagopa.it/mcp
  1. HTTP Headers: leave as is (no headers needed)
  2. Tools: "*" (leave as is)

Use Tab to navigate between fields and Ctrl+S to save.

Available Capabilities​

Tools​

  • pagopa_query_documentation: Query the DX documentation knowledge base using natural language

Learn More​