Crewai Adapter

🚀 CrewAI MCP Adapter

A Python library that extends the CrewAI adapter ecosystem, integrates support for the Model Context Protocol (MCP), and provides comprehensive tools for custom agent and tool development.

🚀 Quick Start

from crewai import Agent, Task
from crewai_adapters import CrewAIAdapterClient
from crewai_adapters.types import AdapterConfig

async def main():
    async with CrewAIAdapterClient() as client:
        # Connect to the MCP server
        await client.connect_to_mcp_server(
            "math",
            command="python",
            args=["math_server.py"]
        )

        # Create an agent and its tools
        agent = Agent(
            name="Calculator",
            goal="Perform calculation operations",
            tools=client.get_tools()
        )

        # Execute a task
        task = Task(
            description="Calculate (3 + 5) × 12",
            agent=agent
        )
        result = await task.execute()
        print(f"Result: {result}")

if __name__ == "__main__":
    import asyncio
    asyncio.run(main())

✨ Features

• 🔌 Native integration with CrewAI and adapter pattern
• 🛠️ Support for the MCP protocol for tool integration
• 🧩 Easy-to-use interface for extending and creating new adapters
• 📝 Type-safe implementation using Pydantic
• 🔍 JSON Schema validation for tool parameters
• 🚀 Asynchronous/await support
• 📊 Detailed execution metadata

📦 Installation

You can install it directly from PyPI:

pip install crewai-adapters

Or install it from the source code:

pip install git+https://github.com/dshivendra/crewai_mcp_adapter.git

💻 Usage Examples

Basic Usage

from crewai import Agent, Task
from crewai_adapters import CrewAIAdapterClient
from crewai_adapters.types import AdapterConfig

async def main():
    async with CrewAIAdapterClient() as client:
        # Connect to the MCP server
        await client.connect_to_mcp_server(
            "math",
            command="python",
            args=["math_server.py"]
        )

        # Create an agent and its tools
        agent = Agent(
            name="Calculator",
            goal="Perform calculation operations",
            tools=client.get_tools()
        )

        # Execute a task
        task = Task(
            description="Calculate (3 + 5) × 12",
            agent=agent
        )
        result = await task.execute()
        print(f"Result: {result}")

if __name__ == "__main__":
    import asyncio
    asyncio.run(main())

📚 Documentation

For detailed documentation, please refer to:

• Getting Started Guide
• API Reference
• Examples

🔧 Technical Details

Prerequisites

• Python 3.11 or higher
• crewai package
• pydantic package
• mcp package

Install Development Dependencies

pip install -e ".[test,docs]"

Run Tests

pytest tests/ -v

📦 Release

To release a new version to PyPI:

1. Update the version number in pyproject.toml.
2. Build the package:

   python -m build
   

3. Upload to PyPI:

   python -m twine upload dist/*
   

📄 License

This project is licensed under the MIT License. Please see the LICENSE file for details.

🤝 Contribution

Contributions are welcome! Please feel free to submit a Pull Request.