MCP Crew Ai

🚀 MCP Team AI Server

The MCP Team AI Server is a lightweight Python-based server designed to run, manage, and create CrewAI workflows. This project uses the Model Context Protocol (MCP) to communicate with Large Language Models (LLMs) and tools (such as Claude Desktop or Cursor IDE), enabling you to effortlessly coordinate multi-agent workflows.

✨ Features

• Automatic Configuration: Automatically load agent and task configurations from two YAML files (agents.yml and tasks.yml), so you don't need to write custom code for basic setup.
• Command-line Flexibility: Pass custom paths to your configuration files via command-line arguments (--agents and --tasks).
• Seamless Workflow Execution: Easily run pre-configured workflows using the MCP run_workflow tool.
• Local Development: Run the server in standard output mode, making it ideal for development and testing.

📦 Installation

There are several ways to install the MCP Team AI Server:

Option 1: Install from PyPI (Recommended)

pip install mcp-crew-ai

Option 2: Install from GitHub

pip install git+https://github.com/adam-paterson/mcp-crew-ai.git

Option 3: Clone and Install

git clone https://github.com/adam-paterson/mcp-crew-ai.git
cd mcp-crew-ai
pip install -e .

Prerequisites

• Python 3.11+
• MCP SDK
• CrewAI
• PyYAML

📚 Configuration

• agents.yml: Define the roles, goals, and backstories of agents.
• tasks.yml: Define task descriptions, expected outputs, and assign them to agents.

Example agents.yml:

zookeeper:
  role: Lion Keeper
  goal: Manage zoo operations
  backstory: >
    You are an experienced zoo keeper with a passion for wildlife conservation...

Example tasks.yml:

write_stories:
  description: >
    Write an engaging zoo update that captures the highlights of the day.
  expected_output: 5 engaging stories
  agent: zookeeper
  output_file: zoo_report.md

💻 Usage Examples

Basic Usage

After installation, you can run the MCP Team AI Server using the following methods:

Standard Python Command

mcp-crew-ai --agents path/to/agents.yml --tasks path/to/tasks.yml

Using UV Execution (uvx)

For a smoother experience, use the UV execution command:

uvx mcp-crew-ai --agents path/to/agents.yml --tasks path/to/tasks.yml

Or run the server directly:

uvx mcp-crew-ai-server

This will start the server with default configuration using environment variables.

Advanced Usage

You can also provide additional variables for your YAML templates:

mcp-crew-ai --agents examples/agents.yml --tasks examples/tasks.yml --topic "Machine Learning" --variables '{"year": 2025, "focus": "Deep Learning"}'

These variables will replace placeholders in the YAML files. For example, {topic} will be replaced with "Machine Learning", and {year} will be replaced with "2025".

Command-line Options

• --agents: Path to the agent YAML file (required)
• --tasks: Path to the task YAML file (required)
• --topic: The main topic of the team's work (default: "Artificial Intelligence")
• --process: The type of processing to use (choices: "sequential" or "hierarchical", default: "sequential")
• --verbose: Enable verbose output
• --variables: JSON string or path to a JSON file containing additional variables for replacement in YAML files
• --version: Display version information and exit

🤝 Contribution

Contributions are welcome! Please open an issue or submit a pull request to help improve the project.

📄 License

[Add license information here]

By following the steps above, you can easily set up and use the MCP Team AI Server to manage complex multi-agent workflows.