Autogen

🚀 Automatic MCP Server Generation

An MCP server integrated with Microsoft's AutoGen framework, enabling multi-agent conversations through standardized interfaces. This server allows you to create and manage AI agents that can collaborate to solve problems through natural language interaction.

🚀 Quick Start

This is an MCP server integrated with the Microsoft AutoGen framework, which enables multi - agent conversations through standardized interfaces. You can create and manage AI agents that collaborate to solve problems via natural language interaction.

✨ Features

• Create and manage customizable AutoGen agents.
• Conduct one - to - one conversations between agents.
• Coordinate group chats among multiple agents.
• Configurable LLM settings and code execution environments.
• Support both assistant - type and user - type agents.
• Built - in error handling and response validation.

📦 Installation

Installation via Smithery

To automatically install the AutoGen Server for Claude Desktop via Smithery:

npx -y @smithery/cli install @DynamicEndpoints/autogen_mcp --client claude

Manual Installation

1. Clone the repository:

git clone https://github.com/yourusername/autogen-mcp.git
cd autogen-mcp

2. Install dependencies:

pip install -e .

📚 Documentation

Environment Variables

1. Copy .env.example to .env:

cp .env.example .env

2. Configure environment variables:

# Configuration file path
AUTOGEN_MCP_CONFIG=config.json

# OpenAI API key (optional, can also be set in config.json)
OPENAI_API_KEY=your-openai-api-key

Server Configuration

1. Copy config.json.example to config.json:

cp config.json.example config.json

2. Configure server settings:

{
  "llm_config": {
    "config_list": [
      {
        "model": "gpt-4",
        "api_key": "your-openai-api-key"
      }
    ],
    "temperature": 0
  },
  "code_execution_config": {
    "work_dir": "workspace",
    "use_docker": false
  }
}

💻 Usage Examples

Available Operations

The server supports three main operations:

1. Create an Agent

{
  "name": "create_agent",
  "arguments": {
    "name": "tech_lead",
    "type": "assistant",
    "system_message": "You are a technical lead with expertise in software architecture and design patterns."
  }
}

2. One - to - One Chat

{
  "name": "execute_chat",
  "arguments": {
    "initiator": "agent1",
    "responder": "agent2",
    "message": "Let's discuss the system architecture."
  }
}

3. Group Chat

{
  "name": "execute_group_chat",
  "arguments": {
    "agents": ["agent1", "agent2", "agent3"],
    "message": "Let's review the proposed solution."
  }
}

Error Handling

Common error scenarios include:

1. Agent Creation Error

{
  "error": "Agent already exists"
}

2. Execution Error

{
  "error": "Agent not found"
}

3. Configuration Error

{
  "error": "AUTOGEN_MCP_CONFIG environment variable is not set"
}

🔧 Technical Details

• AutoGen: The main module that coordinates all operations.
• agents.py: Handles the creation and management of agents.
• chat.py: Implements one - to - one and group chat functions.
• config.py: Manages configuration files and environment variables.

📄 License

[Insert license information here]