Overview
What is Azure AI Agent Service + Azure AI Search MCP Server?
An MCP server that enables Claude Desktop to search content using Azure AI services. It offers two implementations: Azure AI Agent Service (recommended) which provides both document search and web search with source citations, and direct Azure AI Search integration with keyword, vector, and hybrid search methods.
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 (mcp[cli], azure-identity, python-dotenv, etc.), and configure Claude Desktop by adding a server entry pointing to either azure_ai_agent_service_server.py or azure_search_server.py with the required environment variables. Authenticate with Azure using az login and restart Claude Desktop.
Key features of Azure AI Agent Service + Azure AI Search MCP Server
- AI-enhanced search using Azure AI Agent Service
- Search both private indexed documents and the public web
- Web search results include citations to original sources
- Choose between Azure AI Agent Service or direct Azure AI Search
- Seamless integration with Claude Desktop’s interface
- Customizable tools, instructions, and search parameters
Use cases of Azure AI Agent Service + Azure AI Search MCP Server
- Search indexed documents with AI-enhanced results through Claude Desktop
- Perform web searches with source citations for research or fact-checking
- Run hybrid (keyword + vector) searches on Azure AI Search indexes
- Extend Claude Desktop with custom search behaviors and additional tools
FAQ from Azure AI Agent Service + Azure AI Search MCP Server
What does this server do?
It connects Claude Desktop to Azure AI services for searching indexed documents and the web, providing AI-enhanced results and source citations.
What are the two implementation options?
The recommended Azure AI Agent Service implementation uses Azure AI Agent with Bing Web Grounding and Azure AI Search tools. The direct Azure AI Search implementation connects directly to an Azure AI Search index with keyword, vector, and hybrid search methods.
What are the prerequisites?
Python 3.10+, latest Claude Desktop, an Azure subscription with an Azure AI Search service (and optionally an Azure AI Project with Bing connection). Windows or macOS.
Where does the data live?
Your indexed documents reside in Azure AI Search. Web search is performed through Bing (when using the Agent Service). No data is stored by the MCP server itself.
How do I troubleshoot if the server doesn’t 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 from the command line.
