mcp_server
A Model Context Protocol (MCP) server that enables Claude Desktop to search your content using Azure AI services.
The Azure AI Agent Service + Azure AI Search MCP Server provides two implementations to connect Claude Desktop with Azure search capabilities. The recommended Azure AI Agent Service Implementation uses Azure AI Agent Service to offer AI-enhanced document and web search capabilities. Alternatively, the Direct Azure AI Search Implementation connects directly to Azure AI Search, offering keyword, vector, and hybrid search methods. This setup allows users to search both private documents and the public web, with results including source citations. The server is customizable and integrates seamlessly with Claude Desktop.
Features
- AI-Enhanced Search - Optimizes search results with intelligent processing.
- Multiple Data Sources - Search both private documents and the public web.
- Source Citations - Web search results include citations to original sources.
- Flexible Implementation - Choose between Azure AI Agent Service or direct Azure AI Search integration.
- Seamless Claude Integration - All search capabilities accessible through Claude Desktop's interface.
Usage with Different Platforms
Azure AI Agent Service Setup
bash
az login
Azure AI Agent Service Configuration
{
"mcpServers": {
"azure-ai-agent": {
"command": "C:\\path\\to\\.venv\\Scripts\\python.exe",
"args": ["C:\\path\\to\\azure_ai_agent_service_server.py"],
"env": {
"PROJECT_CONNECTION_STRING": "your-project-connection-string",
"MODEL_DEPLOYMENT_NAME": "your-model-deployment-name",
"AI_SEARCH_CONNECTION_NAME": "your-search-connection-name",
"BING_CONNECTION_NAME": "your-bing-connection-name",
"AI_SEARCH_INDEX_NAME": "your-index-name"
}
}
}
}
Direct Azure AI Search Configuration
{
"mcpServers": {
"azure-search": {
"command": "C:\\path\\to\\.venv\\Scripts\\python.exe",
"args": ["C:\\path\\to\\azure_search_server.py"],
"env": {
"AZURE_SEARCH_SERVICE_ENDPOINT": "https://your-service-name.search.windows.net",
"AZURE_SEARCH_INDEX_NAME": "your-index-name",
"AZURE_SEARCH_API_KEY": "your-api-key"
}
}
}
}
Related MCP Servers
View all cloud_platforms servers →edgeone-pages-mcp
by TencentEdgeOne
An MCP service for deploying HTML content, folder, and zip file to EdgeOne Pages and obtaining a publicly accessible URL.
HubSpot
by PipedreamHQ
Pipedream MCP Server is a reference implementation that allows you to run your own MCP server for over 2,500 apps and APIs, powered by Pipedream Connect.
Nx MCP Server
by nrwl
A Model Context Protocol server implementation for Nx, providing LLMs with deep access to monorepo structures.
mcp-atlassian
by sooperset
Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira). This integration supports both Confluence & Jira Cloud and Server/Data Center deployments.
mcp-grafana
by grafana
A Model Context Protocol (MCP) server for Grafana providing access to your Grafana instance and its ecosystem.
firecrawl-mcp-server
by mendableai
Firecrawl MCP Server is a Model Context Protocol server implementation that integrates with Firecrawl for web scraping capabilities.
Figma-Context-MCP
by GLips
Framelink Figma MCP Server allows AI-powered coding tools to access Figma design data, enhancing design implementation accuracy.