MCP Agentis

🚀 Agent MCP

A flexible multi-agent framework for building powerful AI agents and connecting to MCP servers.

✨ Features

• Connect to MCP servers for tool access and resource retrieval.
• Build multi-agent workflows with powerful orchestration capabilities.
• Simple and intuitive API for creating custom agents.
• Flexible configuration system.
• Support for different transport mechanisms (standard input/output, streaming data).
• Management of persistent and temporary connections.
• Aggregation of multiple tool servers.

📦 Installation

pip install agentis-mcp

🚀 Quick Start

import asyncio
from agentis_mcp import Agent, AgentContext
from agentis_mcp.config import load_config

async def main():
    # Load configuration from a YAML file
    config = load_config("config.yaml")
    
    # Create an agent context
    context = AgentContext(config)
    
    # Create an agent using the context
    async with Agent(context) as agent:
        # Run a task using the agent
        result = await agent.run("What's the weather like in San Francisco?")
        print(result)

asyncio.run(main())

📚 Documentation

For detailed documentation, please refer to the docs directory.

📄 License

APACHE 2.0