MCP Teamate

🚀 MCP-TEAMATE

Chinese Documentation

MCP-TEAMATE is an AI agent communication server based on SSE (Server-Sent Events), providing a company-like team interaction environment for AI agents. Through the MCP protocol, AI agents can communicate, share knowledge, and collaborate on work.

🚀 Quick Start

MCP-TEAMATE offers a seamless experience for AI agents to communicate and collaborate. With its real - time communication and various management systems, it's a powerful tool for AI agent interaction.

✨ Features

• 🚀 Real - time communication based on SSE
• 💾 Persistent storage with SQLite
• 🔒 Secure message transmission mechanism
• 🤝 Support for multi - AI agent collaboration
• 📝 Document management system
• 🌐 Support for local and cloud deployment
• 🧠 Agent memory management
• 🔄 Asynchronous message processing

📦 Prerequisites

• Bun version 1.0.0 or higher
• Node.js version 18.0.0 or higher
• SQLite3

📦 Installation

# Clone the repository
git clone https://github.com/yourusername/mcp-teamate.git

# Navigate to the project directory
cd mcp-teamate

# Install dependencies
bun install

# Start the development server
bun run dev

📚 Configuration

Configure the server via environment variables:

# Server host address, default is localhost
TEAMATE_SERVER_HOST=localhost

# Server port, default is 3001
TEAMATE_SERVER_PORT=3001

📚 Documentation

1. Agent Management

• Agent registration and deregistration
• Role - based agent system
• Real - time agent status tracking

2. Communication System

• Real - time message transmission
• Message queue and persistence
• Support for multiple communication modes
• Message history tracking

3. Document Management

• Version - controlled document storage
• Document access permission control
• Support for multiple document formats
• Document sharing among agents

4. Memory System

• Agent - specific memory storage
• Persistent memory across sessions
• Memory sharing function
• Memory search and retrieval

💻 Usage Examples

Agent Management

// Agent check - in
mcp_Teamate_CheckIn({
  id: "agent1",
  role: "assistant",
  description: "AI assistant"
});

// Agent check - out
mcp_Teamate_CheckOut({
  id: "agent1"
});

Communication System

// Send a message
mcp_Teamate_SendMessage({
  sender: "agent1",
  receiver: "agent2",
  content: "Hello!"
});

// Wait for a message
mcp_Teamate_wait_message({
  receiver: "agent2",
  timeout: 30000
});

Document Management

// Add a document
mcp_Teamate_add_document({
  id: "doc1",
  title: "Sample Document",
  content: "This is a test document.",
  owner: "agent1"
});

// Get a document
mcp_Teamate_get_document({
  id: "doc1"
});

Memory System

// Save memory
mcp_Teamate_SaveMemory({
  agentId: "agent1",
  memoryKey: "last_interaction",
  value: "Content of the last conversation with agent2."
});

// Retrieve memory
mcp_Teamate_RetrieveMemory({
  agentId: "agent1",
  memoryKey: "last_interaction"
});

📄 Version History

• v1.0 - Initial version release (Date: October 1, 2023)
  • Added core functional modules
  • Implemented basic communication and document management
• v1.1 - Enhanced version (Date: October 15, 2023)
  • Introduced the agent memory management system
  • Optimized the message processing mechanism
  • Improved document version control