AgentMCP: The Universal System for AI Agent Collaboration

Unleashing a new era of AI collaboration: AgentMCP is the system that makes any AI agent work with every other agent - handling all the networking, communication, and coordination between them. Together with MACNet (The Internet of AI Agents), we're creating a world where AI agents can seamlessly collaborate across any framework, protocol, or location.

✨ The Magic: Transform Your Agent in 30 Seconds

Turn any existing AI agent into a globally connected collaborator with just one line of code.

pip install agent-mcp  # Step 1: Install

from agent_mcp import mcp_agent  # Step 2: Import

@mcp_agent(mcp_id="MyAgent")      # Step 3: Add this one decorator! 🎉
class MyExistingAgent:
    # ... your agent's existing code ...
    def analyze(self, data):
        return "Analysis complete!"

That's it! Your agent is now connected to the Multi-Agent Collaboration Network (MACNet), ready to work with any other agent, regardless of its framework.

➡️ Jump to Quick Demos to see it live! ⬅️

What is AgentMCP?

AgentMCP is the world's first universal system for AI agent collaboration. Just as operating systems and networking protocols enabled the Internet, AgentMCP handles all the complex work needed to make AI agents work together:

• Converting agents to speak a common language
• Managing network connections and discovery
• Coordinating tasks and communication
• Ensuring secure and reliable collaboration

With a single decorator, developers can connect their agents to MACNet (our Internet of AI Agents), and AgentMCP takes care of everything else - the networking, translation, coordination, and collaboration. No matter what framework or protocol your agent uses, AgentMCP makes it instantly compatible with our global network of AI agents.

📚 Examples

🚀 Quick Demos: See AgentMCP in Action!

These examples show the core power of AgentMCP. See how easy it is to connect agents and get them collaborating!

1. Simple Multi-Agent Chat (Group Chat)

Watch two agents built with different frameworks (Autogen and LangGraph) chat seamlessly.

The Magic: The @mcp_agent decorator instantly connects them.

From demos/basic/simple_chat.py:

# --- Autogen Agent --- 
@mcp_agent(mcp_id="AutoGen_Alice")
class AutogenAgent(autogen.ConversableAgent):
    # ... agent code ...

# --- LangGraph Agent --- 
@mcp_agent(mcp_id="LangGraph_Bob")
class LangGraphAgent:
    # ... agent code ...

What it shows:

• Basic agent-to-agent communication across frameworks.
• How @mcp_agent instantly connects agents to the network.
• The foundation of collaborative work.

Run it:

python demos/network/test_deployed_network.py

3. Multi-Provider Cost Optimization (NEW!)

See how AgentMCP automatically reduces costs by 80-90% through intelligent provider selection.

The Magic:

• Automatic Provider Routing: Chooses most cost-effective AI provider for each task
• Quality Preservation: Maintains high quality while reducing costs
• Real-time Optimization: Continuously optimizes based on task requirements