Crewai (Near Intents)

🚀 Group AI MCP Server

An MCP server based on the CrewAI framework that provides AI agent and task management capabilities.

🚀 Quick Start

📦 Installation

1. Clone or fork this repository.
2. Run the installation script:

./crew.sh

This script will:

• Install the required Python dependencies.
• Configure the MCP settings file suitable for your system.
• Automatically set the correct paths.

⚙️ Configuration

Before using the server, set your OpenAI API key:

export OPENAI_API_KEY="your-api-key"

💻 Usage Examples

🔍 Basic Usage

The server provides three main tools:

1. Create an Agent

{
    "method": "call_tool",
    "params": {
        "name": "create_agent",
        "arguments": {
            "role": "Researcher",
            "goal": "Effectively research and analyze information",
            "backstory": "An experienced data analyst"
        }
    }
}

2. Create a Task

{
    "method": "call_tool",
    "params": {
        "name": "create_task",
        "arguments": {
            "description": "Analyze recent market trends",
            "agent": "Researcher",
            "expected_output": "A detailed analysis report"
        }
    }
}

3. Create and Run a Team

{
    "method": "call_tool",
    "params": {
        "name": "create_crew",
        "arguments": {
            "agents": ["Researcher"],
            "tasks": ["Analyze recent market trends"],
            "verbose": true
        }
    }
}

💡 Advanced Usage

Create and run a complete process:

(echo '{"method": "call_tool", "params": {"name": "create_agent", "arguments": {"role": "Researcher", "goal": "Effectively research and analyze information", "backstory": "An experienced data analyst"}}}'; echo '{"method": "call_tool", "params": {"name": "create_task", "arguments": {"description": "Analyze recent market trends", "agent": "Researcher", "expected_output": "A detailed analysis report"}}}'; echo '{"method": "call_tool", "params": {"name": "create_crew", "arguments": {"agents": ["Researcher"], "tasks": ["Analyze recent market trends"], "verbose": true}}}') | python3 src/crew_server.py

📚 Documentation

🛠️ System Requirements

• Python 3.8 or higher.
• The jq command-line tool (for the installation script).
• VSCode with the Roo Cline extension installed.

🌐 Supported Platforms

• macOS
• Linux
• Windows (via Git Bash)

🐞 Troubleshooting

If you encounter problems:

1. Ensure that the OpenAI API key is set correctly.
2. Confirm that all dependencies are installed.
3. Check if the MCP settings file is configured correctly.
4. Make sure the server path is correct.

🤝 Contribution Guidelines

The process is as follows:

1. Fork the repository.
2. Create a feature branch.
3. Commit your code.
4. Submit a pull request.

This document provides you with a clear getting-started guide, detailing everything from installation and configuration to usage and troubleshooting. Although some specific operation steps may not be entirely clear, following the document step by step should work fine. Next, you can try cloning the repository, running the installation script, and then creating agents, tasks, and teams according to the examples to see the actual results.