drio
Open app

MCP Server that interacts with Azure AI Foundry (experimental)

Source

A MCP Server for Azure AI Foundry

Catalog onlyCatalog onlySTDIO

Overview

MCP Foundry is an Azure AI Agent Service MCP Server that integrates with Azure AI Foundry, enabling connections to existing Azure AI Agents and utilizing various models and knowledge tools available within Azure AI Foundry.

To use MCP Foundry, set up your Azure AI Agents, configure the server with your project connection string and agent IDs, and run the server to connect with any MCP-compatible client.

  • 🤖 Agent Integration: Connect to your existing Azure AI Agents. - 🔄 Seamless Workflow: Use your agents directly within any MCP client. - 🛡️ Secure: All connections use your Azure credentials. - 🧠 Conversation Memory: Each client session maintains isolated conversation history.
  1. Integrating Azure AI Agents into custom applications.
  2. Facilitating seamless communication between multiple AI agents.
  3. Enhancing AI capabilities in existing projects with Azure AI tools.

Add to your AI client

Use these steps to connect MCP Server that interacts with Azure AI Foundry (experimental) in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "mcp-foundry-azure-ai-foundry": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-foundry-azure-ai-foundry"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "mcp-foundry-azure-ai-foundry": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-foundry-azure-ai-foundry"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "mcp-foundry-azure-ai-foundry": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-foundry-azure-ai-foundry"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "mcp-foundry-azure-ai-foundry": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-foundry-azure-ai-foundry"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-foundry-azure-ai-foundry": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-foundry-azure-ai-foundry"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "mcp-foundry-azure-ai-foundry": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-foundry-azure-ai-foundry"
      ]
    }
  }
}

FAQ

How do I set up my Azure AI Agents?

You can create Azure AI Agents through Azure AI Foundry and note your connection string and agent IDs for configuration.

Is there a specific programming language required?

The server is built using Python, and you need Python 3.10+ to run it.

What is the license for MCP Foundry?

MCP Foundry is licensed under the MIT License, allowing free use, modification, and distribution.7:["$","di

Developer tools