Azure AI Agents
Model Context Protocol Servers for Azure AI Search
What is Azure AI Agents?
Azure AI Agents is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol servers for azure ai search
Model Context Protocol Servers for Azure AI Search
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Model Context Protocol Servers for Azure AI Search
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx azure-ai-agentsConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Azure AI Agents
The Azure AI Agents MCP server connects Claude Desktop and other MCP clients to Azure AI Search and Azure AI Agent Service, giving AI assistants the ability to search private document indexes and query the web with Bing grounding. It offers two implementation paths: the recommended Azure AI Agent Service path for AI-enhanced search with source citations, and a direct Azure AI Search path supporting keyword, vector, and hybrid search. This server is ideal for teams that maintain document indexes in Azure and want their AI assistant to retrieve grounded, cited answers from that data.
Prerequisites
- Python 3.10 or higher
- An Azure subscription with an Azure AI Search service and a populated index with vectorized text
- For the Agent Service path: an Azure AI Project with Azure AI Search and Bing Web Search connections configured
- Azure CLI installed and authenticated via 'az login'
- An MCP-compatible client such as Claude Desktop
Clone the repository
Clone the mcp-server-azure-ai-agents repository to your machine.
git clone https://github.com/farzad528/mcp-server-azure-ai-agents.git
cd mcp-server-azure-ai-agentsSet up a Python virtual environment
Create and activate a virtual environment using uv.
uv venv
.venv\Scripts\activate # Windows
# or: source .venv/bin/activate # macOS/LinuxInstall dependencies for the Agent Service path
Install the MCP CLI, Azure identity, and Azure AI Projects packages.
uv pip install "mcp[cli]" azure-identity python-dotenv azure-ai-projectsCreate the .env file with your Azure credentials
Create a .env file with your Azure AI Project connection string and related configuration values.
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-nameAuthenticate with Azure
Log in with the Azure CLI so the server can use DefaultAzureCredential for authentication.
az loginConfigure Claude Desktop
Add the MCP server configuration to your claude_desktop_config.json, pointing to the agent service server script.
Azure AI Agents Examples
Client configuration
Add this to your claude_desktop_config.json to connect Claude Desktop to the Azure AI Agent Service MCP server. Update all path and credential placeholders with your actual values.
{
"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"
}
}
}
}Prompts to try
Once connected, use these prompts to search your Azure documents and the web through Claude.
- "Search my Azure documents for the quarterly financial report"
- "Find information about our product roadmap in the internal knowledge base"
- "Search the web for recent Azure AI Search updates and summarize them with sources"
- "Use hybrid search to find documents about customer onboarding procedures"Troubleshooting Azure AI Agents
Authentication errors when the server starts
Run 'az login' in the terminal where you will launch the server. Ensure your Azure account has the 'Cognitive Services User' role on the AI Search resource and contributor access to the AI Project.
Index not found or empty search results
Verify AI_SEARCH_INDEX_NAME matches exactly (case-sensitive) the index name in your Azure AI Search portal. Ensure the index contains documents and that the vectorizer is configured if using vector or hybrid search.
Bing grounding tool not available
Confirm that a Bing Web Search connection is created in your Azure AI Project and that BING_CONNECTION_NAME in the .env file matches the connection name exactly as shown in the Azure AI Studio portal.
Frequently Asked Questions about Azure AI Agents
What is Azure AI Agents?
Azure AI Agents is a Model Context Protocol (MCP) server that model context protocol servers for azure ai search It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Azure AI Agents?
Follow the installation instructions on the Azure AI Agents GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Azure AI Agents?
Azure AI Agents works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Azure AI Agents free to use?
Yes, Azure AI Agents is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Azure AI Agents Alternatives — Similar Cloud Services Servers
Looking for alternatives to Azure AI Agents? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Azure AI Agents in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Azure AI Agents?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.