drio
Open app

Azure AI Agent Service + Azure AI Search MCP Server

Source

Model Context Protocol Servers for Azure AI Search

Catalog onlyCatalog onlySTDIO

Overview

This project provides a Model Context Protocol (MCP) server that connects Claude Desktop with Azure AI services, enabling enhanced search capabilities through both document and web search.

To use the MCP server, set up the environment by creating a .env file with your Azure project details, install the necessary dependencies, and run the server script for either the Azure AI Agent Service or direct Azure AI Search integration.

  • AI-enhanced search results through Azure AI Agent Service. - Multiple search methods: keyword, vector, and hybrid search. - Source citations for web search results. - Seamless integration with Claude Desktop. - Customizable search behavior.
  1. Searching indexed documents with AI-enhanced results.
  2. Conducting web searches with source citations.
  3. Utilizing semantic similarity for improved search accuracy.

Add to your AI client

Use these steps to connect Azure AI Agent Service + Azure AI Search MCP Server 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-server-azure-ai-agents-farzad528": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-azure-ai-agents-farzad528"
      ]
    }
  }
}

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-server-azure-ai-agents-farzad528": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-azure-ai-agents-farzad528"
      ]
    }
  }
}

Claude Code

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

.mcp.json (project root)

{
  "mcpServers": {
    "mcp-server-azure-ai-agents-farzad528": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-azure-ai-agents-farzad528"
      ]
    }
  }
}

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-server-azure-ai-agents-farzad528": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-azure-ai-agents-farzad528"
      ]
    }
  }
}

Windsurf

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

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-server-azure-ai-agents-farzad528": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-azure-ai-agents-farzad528"
      ]
    }
  }
}

Cline

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

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "mcp-server-azure-ai-agents-farzad528": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-azure-ai-agents-farzad528"
      ]
    }
  }
}
Research and data