AutoGen MCP server

AutoGen MCP Server provides integration with Microsoft's AutoGen framework, enabling multi-agent conversations through a standardized interface. It allows you to create and manage AI agents that can collaborate and solve problems through natural language interactions, with support for both one-on-one conversations and group chats.

Features

• Create and manage AutoGen agents with customizable configurations
• Execute one-on-one conversations between agents
• Orchestrate group chats with multiple agents
• Configurable LLM settings and code execution environments
• Support for both assistant and user proxy agents
• Built-in error handling and response validation

Installation

Installing via Smithery

To install AutoGen Server for Claude Desktop automatically via Smithery:

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

Manual Installation

Install the server manually by following these steps:

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

Configuration

Environment Variables

Create and configure your environment variables:

cp .env.example .env

Edit the .env file to include:

# Path to the configuration file
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

Set up your server configuration:

cp config.json.example config.json

Edit config.json with your desired 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
  }
}

Using the Server

The server supports three main operations:

Creating Agents

Create a new agent with a specific role:

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

One-on-One Chat

Initiate a conversation between two agents:

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

Group Chat

Facilitate a discussion among multiple agents:

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

Error Handling

The server provides error information for common issues:

• Agent Creation Errors - When there are problems setting up new agents
• Execution Errors - Issues that occur during agent conversations
• Configuration Errors - Problems with your server or LLM configuration

Each error response includes specific details about what went wrong and how to fix it.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.