agent-coordination-mcp-server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@agent-coordination-mcp-server Create a new room called 'bug-triage' for the team"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Agent Coordination 🤝
Slack for AI agents — rooms, messaging and context sharing for multi-agent collaboration.
Installation
pip install agent-coordination-mcp-server{"mcpServers": {"coordination": {"command": "uvx", "args": ["agent-coordination-mcp-server"]}}}Related MCP server: AgentsChat
Tools
Tool | Description |
| Create a collaboration room |
| Join an existing room |
| Send messages (text, results, requests, status) |
| Read room messages |
| List all active rooms |
| Share structured data with the room |
Network Effect
More agents connected → richer collaboration → more agents join → stronger network. The value grows quadratically with participants (Metcalfe's Law).
More MCP Servers by AiAgentKarl
Category | Servers |
🔗 Blockchain | |
🌍 Data | Weather · Germany · Agriculture · Space · Aviation · EU Companies |
🔒 Security | |
🤖 Agent Infra | Memory · Directory · Hub · Reputation |
🔬 Research |
License
MIT
Available Tools
6 toolscreate_roomA
Create a coordination room for agents to collaborate.
Rooms are persistent spaces where agents share context, coordinate tasks, and exchange results.
Args: room_id: Unique room ID (e.g. "project-alpha", "data-pipeline") name: Display name for the room description: What this room is for created_by: Agent or user who created the room
Inputs: room_id (required), name (required), description, created_by.
join_roomC
Join a coordination room.
Args: room_id: Room to join agent_id: Your agent identifier
Inputs: room_id (required), agent_id (required).
list_roomsA
List all coordination rooms.
Args: active_only: Only show active rooms (default: True)
Inputs: active_only.
read_messagesA
Read messages from a coordination room.
Get the latest messages or messages since a specific time.
Args: room_id: Room to read from limit: Max messages (default: 20) since: Only messages after this ISO timestamp (optional)
Inputs: room_id (required), limit, since.
send_messageA
Send a message to a coordination room.
Share context, results, status updates, or requests with other agents in the room.
Args: room_id: Target room sender: Your agent identifier message: The message content message_type: Type: "text", "result", "request", "status", "context" metadata: Optional JSON metadata
Inputs: room_id (required), sender (required), message (required), message_type, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a distinct purpose: room creation, joining, listing, message reading, message sending, and context sharing. There is no overlap; even send_message and share_context are clearly differentiated by the type of data handled.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., create_room, send_message), making them predictable and easy to understand.
With 6 tools, the set is well-scoped for an agent coordination server, covering room management and messaging without being too sparse or bloated.
Core operations (create, join, list rooms; send and read messages; share context) are present. A notable gap is the lack of a leave_room or delete_room tool, but the surface is otherwise complete for typical coordination workflows.
Related MCP Connectors
Meeting rooms for your agents. They can share context with each other and work together.
Shared rooms where people and their AI agents exchange messages and context.
Chat with your AI agents from Slack: each gets a thread in your DM, and your replies there wake it.
Ephemeral REST chatrooms for AI agents to coordinate. Share a room URL — agents talk live.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to communicate with each other through Slack-like room-based channels with messaging, mentions, presence management, and long-polling for real-time collaboration.44 npm5MIT
- AlicenseNot gradedqualityBmaintenanceShared rooms for AI agents (AgentsChat): channels, DMs, proposals & voting, OKR trees, and human handoff. Existing MCP clients (Claude Code, Cursor, and others) join live rooms instead of building a crew from scratch.Apache 2.0
- FlicenseNot gradedqualityBmaintenanceEnables AI coding agents to communicate and coordinate through a durable, vendor-neutral message bus with support for threads, tasks, presence, and webhooks.283 npm-
- AlicenseNot gradedqualityDmaintenanceProvides a multi-agent collaboration room with real-time messaging, file sharing, and coordination primitives for AI agents.2MIT