MCP Foundry

🚀 Azure AI Agent Service MCP Server

This MCP server integrates with Azure AI Foundry to connect to your existing Azure AI agents, leveraging a wide range of models and knowledge tools available in Azure AI Foundry, such as Azure AI Search and Bing Web Foundation.

🚀 Quick Start

This MCP server integrates with Azure AI Foundry, enabling seamless connections to your existing Azure AI agents. It allows you to take advantage of the extensive models and knowledge tools provided by Azure AI Foundry, such as Azure AI Search and Bing Web Foundation.

✨ Features

This project offers the following features:

1. Agent Integration: Connect to Azure AI agents.
2. Seamless Workflow: Provide a smooth interaction experience.
3. Scalability: Support large-scale deployments.

💻 Usage Examples

Basic Usage

connect (v1)

# Connect to the Azure AI agent

config (v1)

// Configuration settings
{
  "connection": {
    "type": "AzureAI"
  }
}

📦 Installation

Environment Variables

• PROJECT_CONNECTION_STRING: Project connection string.
• DEFAULT_AGENT_ID: Default agent ID.

Installation Instructions

Python Version

1. Activate the virtual environment:

   # Run from the project root directory
   cd src/python
   python -m venv .venv
   source .venv/bin/activate
   

2. Install dependencies:

   pip install --upgrade .
   

3. Run the server:

   python -m azure_agent_service
   

TypeScript Version

1. Install dependencies:

   cd src/typescript
   npm install
   

2. Build the project:

   npm run build
   

3. Start the server:

   npm start
   

📚 Documentation

Use with Other MCP Clients

This server adheres to the MCP protocol specification and can be used with any compatible client. Please refer to the documentation of the client you are using for specific connection methods.

🔧 Technical Details

This project adopts a multi - language structure:

Python Development

1. Python code is located in the src/python directory.
2. Always activate the virtual environment at the project root directory.
3. When installing packages, ensure that you are operating in the directory containing pyproject.toml.

TypeScript Development

1. TypeScript code is located in the src/typescript directory.
2. Use ES modules for modern JavaScript compatibility development.
3. Follow the standard npm workflow: npm install → npm run build → npm start

📄 License

This project is released under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please refer to the LICENSE file in the project repository.