Get the FREE Ultimate OpenClaw Setup Guide →

mcp -agent-comm

MCP server from KhaiHuynhVN/mcp-server-agent-comm

Installation
Run this command in your terminal to add the MCP server to Claude Code.
Run in terminal:
Command
claude mcp add --transport stdio khaihuynhvn-mcp-server-agent-comm python E:/MCP-servers-github/Utils/mcp_server_agent1.py

How to use

This MCP server implements a dual-agent communication system where two agents collaborate through a centralized Controller UI. It supports real-time message routing, admin control with absolute priority, and a rule-based language system (Vietnamese and English). Use the provided agentChat tools to initialize and route messages between Agent 1 and Agent 2, and leverage the Controller UI for monitoring, routing, and managing the message queue. The system is designed for mixed content (text, files, images) and includes a priority mechanism where admin commands take precedence over agent messages. To get started, start both agent MCP servers and use the Controller UI to register, route, and monitor the two agents during conversations.

How to install

Prerequisites:

  • Python installed on the host machine
  • MCP-compatible environment prepared (e.g., Claude, Cursor) or equivalent integration
  • Git for cloning the repository

Step 1: Clone the repository

git clone https://github.com/your-repo/mcp-server-agent-comm.git
cd mcp-server-agent-comm

Step 2: Install dependencies

pip install -r requirements.txt

Step 3: Configure MCP settings for the agent chats Add the following configuration to your MCP settings (adjust paths as needed):

{
  "agent_chat_1": {
    "command": "python",
    "args": ["E:/MCP-servers-github/Utils/mcp_server_agent1.py"],
    "stdio": true,
    "enabled": true
  },
  "agent_chat_2": {
    "command": "python",
    "args": ["E:/MCP-servers-github/Utils/mcp_server_agent2.py"],
    "stdio": true,
    "enabled": true
  }
}

Note: Update the path to match your actual installation directory.

Step 4: Start the controllers and agents as needed by your environment and MCP setup.

Additional notes

Tips and considerations:

  • Ensure Python path and environment variables are correctly configured in your MCP setup to avoid startup errors.
  • If agents fail to communicate, verify that both agents are registered in the Controller UI and that the rule files (Vietnamese EN or VI) are correctly loaded.
  • For debugging, check the shared_data directory permissions and perform a clean restart of MCP servers if the message queue or routing appears stuck.
  • The admin priority system uses a SOURCE tag; admin messages override all agent activities unless overridden by specific configuration.
  • File and image attachments are supported through the UI controller and routing system; ensure proper permissions for the file storage locations.
  • When upgrading or migrating, preserve the agent configuration blocks and rule files to maintain behavior consistency.

Related MCP Servers

Sponsor this space

Reach thousands of developers