mcpField
M
MCP-TEAMATE

MCP-TEAMATE

Local
github.com/aokihuAI & Agents3Updated 73w ago

About MCP-TEAMATE

MCP-TEAMATE is an AI agent communication server for teams that need agents to coordinate, share information, and work together. It combines httpstream messaging with persistent documents and agent memory.

Key features

  1. 01Real-time httpstream communication
  2. 02SQLite persistent storage
  3. 03Agent registration and role management
  4. 04Versioned document sharing
  5. 05Persistent agent memory
  6. 06Asynchronous message processing

Use cases

  1. 01Coordinate messages between AI agents
  2. 02Share and manage team documents
  3. 03Retrieve agent-specific memory across sessions

MCP support

The server uses MCP to let AI agents communicate, share knowledge, and collaborate through its agent, messaging, document, and memory capabilities.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP-TEAMATE


中文文档

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


Features

  • 🚀 Real-time communication based on httpstream
  • 💾 SQLite persistent storage
  • 🔒 Secure message delivery mechanism
  • 🤝 Multi-AI agent collaboration
  • 📝 Document management system
  • 🌐 Support for both local and cloud deployment
  • 🧠 Agent memory management
  • 🔄 Asynchronous message processing

Prerequisites

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

Installation

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

# Navigate to project directory
cd mcp-teamate

# Install dependencies, optional
bun install

# Start development server
bun run dev

Configuration

Server can be configured through environment variables:

# Server host address, defaults to localhost
TEAMATE_SERVER_HOST=localhost

# Server port, defaults to 3001
TEAMATE_SERVER_PORT=3001

# Set port and run
TEAMATE_SERVER_PORT=3001 bun run dev

# Set host and port and run
TEAMATE_SERVER_HOST=0.0.0.0 TEAMATE_SERVER_PORT=3001 bun run dev

Core Features

1. Agent Management
  • Agent registration and deregistration
  • Role-based agent system
  • Real-time agent status tracking
2. Communication System
  • Real-time message delivery
  • Message queuing and persistence
  • Support for multiple communication patterns
  • Message history tracking
3. Document Management
  • Version-controlled document storage
  • Document access control
  • Support for multiple document formats
  • Document sharing between agents
4. Memory System
  • Agent-specific memory storage
  • Persistent memory across sessions
  • Memory sharing capabilities
  • Memory search and retrieval

API Overview

Agent Management
// Agent Check-in
mcp_Teamate_check_in({
  id: "agent1",
  role: "assistant",
  description: "AI Assistant"
});

// Agent Check-out
mcp_Teamate_check_out({
  id: "agent1"
});

// Get all agents
mcp_Teamate_get_all_agents({});

// Add Memory
mcp_Teamate_add_memory({
  id: "agent1",
  memory: "Important information"
});

// Read Memory
mcp_Teamate_read_memory({
  id: "agent1"
});

// Delete Memory
mcp_Teamate_delete_memory({
  id: "agent1"
});
Communication
// Send Message
mcp_Teamate_send_message({
  sender: "agent1",
  receiver: "agent2",
  content: "Hello!"
});

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

// Get all messages for a receiver
mcp_Teamate_get_all_messages({
  receiver: "agent2"
});

// Get a message by ID
mcp_Teamate_get_message({
  id: "message_id"
});

// Delete a message by ID
mcp_Teamate_delete_message({
  id: "message_id"
});
Document Management
// Add Document
mcp_Teamate_add_document({
  slug: "doc1",
  title: "Example Document",
  content: "Document content",
  maintainer: "agent1",
  version: "1.0.0"
});

// Delete Document
mcp_Teamate_delete_document({
  slug: "doc1",
  secretKey: "your_secret_key"
});

// Get All Documents
mcp_Teamate_get_all_documents({});

// Get Document
mcp_Teamate_get_document({
  slug: "doc1"
});

// Update Document
mcp_Teamate_update_document({
  slug: "doc1",
  content: "Updated content",
  secretKey: "your_secret_key",
  version: "1.0.1"
});

Development

# Run development server
bun run dev

# Build project
bun run build

# Compile project
bun run compile

Contributing

We welcome contributions! Please feel free to submit a Pull Request.

License

MIT

Author

aokihu [email protected]

Version History

  • 4.1.0 - Current version
    • Replaced SSE with httpstream for real-time communication
  • 3.3.1 - Previous version
    • Fixed document management system parameter order bug
    • Improved document content storage reliability
  • 3.3.0 - Previous version
    • Added support for multiple communication patterns
    • Enhanced document management system
    • Improved error handling and logging
  • 3.2.1 - Previous version
    • Added document management system
    • Enhanced memory management
    • Improved message delivery system
  • 3.1.0 - Added memory management
  • 3.0.0 - Migration to SSE communication

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.