Azure AI Agent Service + Azure AI Search MCP Server

What is Azure AI Agent Service + Azure AI Search MCP Server?

A Model Context Protocol server that enables Claude Desktop to search content using Azure AI services. It offers two implementations: Azure AI Agent Service (with document search and web search) or direct Azure AI Search integration. Designed for users who need AI-enhanced search over private documents and the public web through Claude Desktop.

How to use Azure AI Agent Service + Azure AI Search MCP Server?

Install Python 3.10+, set up a virtual environment with uv, install dependencies, create a .env file with Azure credentials, and configure Claude Desktop's mcpServers JSON with the appropriate script path and environment variables for your chosen implementation.

Key features of Azure AI Agent Service + Azure AI Search MCP Server

• AI-enhanced search using Azure AI Agent Service
• Search both private documents and the public web
• Web search results include source citations
• Choose between Agent Service or direct Azure AI Search integration
• Seamless access through Claude Desktop's interface
• Customizable via decorators and tool instructions

Use cases of Azure AI Agent Service + Azure AI Search MCP Server

• Search indexed documents with AI-enhanced results via Claude Desktop
• Perform web searches with source citations using Bing grounding
• Run keyword, vector, or hybrid searches on Azure AI Search indexes
• Extend search behavior by adding custom tools or modifying instructions

FAQ from Azure AI Agent Service + Azure AI Search MCP Server

What are the requirements?

Python 3.10+, latest Claude Desktop, an Azure AI Search service with an indexed dataset, and (for Agent Service) an Azure AI Project with Azure AI Search and Bing connections. Supported on Windows and macOS.

How do I troubleshoot if the server does not appear in Claude Desktop?

Check Claude Desktop logs at %APPDATA%\Claude\logs\mcp*.log (Windows), verify file paths and environment variables in the configuration, and test running the server directly with python azure_ai_agent_service_server.py.

Which implementation should I choose?

Azure AI Agent Service is recommended. It provides both document search (via Azure AI Search tool) and web search (via Bing grounding). Direct Azure AI Search is also available for keyword, vector, or hybrid search without the Agent Service.

How can I customize the server?

Modify tool instructions to change query processing, add new tools using the @mcp.tool() decorator, customize response formatting, or adjust web search parameters to focus on specific domains.

Where does my data live?

All data stays within your Azure resources (Azure AI Search index, Azure AI Project, Bing connection). The MCP server runs locally on your machine and communicates directly with your Azure services.