Azure AI Agent Service + Azure AI Search MCP Server

Overview

1. Azure AI Agent Service Implementation (Recommended) - Uses the powerful Azure AI Agent Service to provide:

2. Direct Azure AI Search Implementation - Connects directly to Azure AI Search with three methods:

Features

• AI-Enhanced Search - Azure AI Agent Service optimizes search results with intelligent processing

• Multiple Data Sources - Search both your 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

• Customizable - Easy to extend or modify search behavior

Quick Links

• Get Started with Azure AI Search

• Azure AI Agent Service Quickstart

Requirements

• Python: Version 3.10 or higher

• Claude Desktop: Latest version

• Azure Resources:

• Operating System: Windows or macOS (instructions provided for Windows, but adaptable)

Azure AI Agent Service Implementation (Recommended)

Setup Guide

1. Project Directory:

2. Create a `.env` File:

3. Set Up Virtual Environment:

4. Use the `azure_ai_agent_service_server.py` script for integration with Azure AI Agent Service.

Azure AI Agent Service Setup

1. Create an Azure AI Project:

2. Create an Azure AI Search Connection:

3. Create a Bing Web Search Connection:

4. Authenticate with Azure:

Configuring Claude Desktop

Note: Replace path placeholders with your actual project paths.

Direct Azure AI Search Implementation

1. Create a different `.env` File:

2. Install Dependencies:

3. Use the `azure_search_server.py` script for direct integration with Azure AI Search.

4. Configure Claude Desktop:

Testing the Server

1. Restart Claude Desktop to load the new configuration

2. Look for the MCP tools icon (hammer icon) in the bottom-right of the input field

3. Try queries such as:

Troubleshooting

• Server Not Appearing:

• Azure AI Agent Service Issues:

Customizing Your Server

• Modify Tool Instructions: Adjust the instructions provided to each agent to change how they process queries

• Add New Tools: Use the @mcp.tool() decorator to integrate additional tools

• Customize Response Formatting: Edit how responses are formatted and returned to Claude Desktop

• Adjust Web Search Parameters: Modify the web search tool to focus on specific domains

License

Azure AI Agent Service + Azure AI Search MCP Server

Overview

1. Azure AI Agent Service Implementation (Recommended) - Uses the powerful Azure AI Agent Service to provide:

2. Direct Azure AI Search Implementation - Connects directly to Azure AI Search with three methods:

Features

• AI-Enhanced Search - Azure AI Agent Service optimizes search results with intelligent processing

• Multiple Data Sources - Search both your 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

• Customizable - Easy to extend or modify search behavior

Quick Links

• Get Started with Azure AI Search

• Azure AI Agent Service Quickstart

Requirements

• Python: Version 3.10 or higher

• Claude Desktop: Latest version

• Azure Resources:

• Operating System: Windows or macOS (instructions provided for Windows, but adaptable)

Azure AI Agent Service Implementation (Recommended)

Setup Guide

1. Project Directory:

2. Create a `.env` File:

3. Set Up Virtual Environment:

4. Use the `azure_ai_agent_service_server.py` script for integration with Azure AI Agent Service.

Azure AI Agent Service Setup

1. Create an Azure AI Project:

2. Create an Azure AI Search Connection:

3. Create a Bing Web Search Connection:

4. Authenticate with Azure:

Configuring Claude Desktop

Note: Replace path placeholders with your actual project paths.

Direct Azure AI Search Implementation

1. Create a different `.env` File:

2. Install Dependencies:

3. Use the `azure_search_server.py` script for direct integration with Azure AI Search.

4. Configure Claude Desktop:

Testing the Server

1. Restart Claude Desktop to load the new configuration

2. Look for the MCP tools icon (hammer icon) in the bottom-right of the input field

3. Try queries such as:

Troubleshooting

• Server Not Appearing:

• Azure AI Agent Service Issues:

Customizing Your Server

• Modify Tool Instructions: Adjust the instructions provided to each agent to change how they process queries

• Add New Tools: Use the @mcp.tool() decorator to integrate additional tools

• Customize Response Formatting: Edit how responses are formatted and returned to Claude Desktop

• Adjust Web Search Parameters: Modify the web search tool to focus on specific domains

License