
Cross-System Agent Communication
STDIOCommunication and coordination system for collaborative LLM agents across multiple systems.
Communication and coordination system for collaborative LLM agents across multiple systems.
This MCP server enables communication and coordination between different Roo modes/roles across multiple systems. It creates a "team of agents" architecture where specialized LLM agents can collaborate on tasks, share context, and coordinate work.
The Cross-System Agent Communication MCP Server consists of three main components:
Core MCP Server
GitHub Integration Layer
PlanetScale Database Layer
Clone the repository:
git clone https://github.com/mkc909/agent-communication-mcp-server.git
cd agent-communication-mcp-server
Install dependencies:
npm install
Create a .env
file with the following variables:
GITHUB_TOKEN=your_github_token
PLANETSCALE_HOST=your_planetscale_host
PLANETSCALE_USERNAME=your_planetscale_username
PLANETSCALE_PASSWORD=your_planetscale_password
Build the project:
npm run build
Start the server:
npm start
npm run dev
npm test
npm run lint
register_agent
: Register a new agentupdate_agent
: Update agent informationget_agent
: Get agent informationlist_agents
: List all registered agentssend_message
: Send message to another agentget_messages
: Get messages for an agentmark_message_read
: Mark message as readdelete_message
: Delete a messagecreate_task
: Create a new taskassign_task
: Assign task to an agentupdate_task_status
: Update task statusget_task
: Get task detailslist_tasks
: List taskscreate_context
: Create shared contextupdate_context
: Update shared contextshare_context
: Share context with agentget_context
: Get shared contextlist_contexts
: List shared contextsgithub_create_issue
: Create GitHub issuegithub_comment_issue
: Comment on GitHub issuegithub_create_pr
: Create GitHub PRgithub_review_pr
: Review GitHub PRMIT