mcp-comms
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., "@mcp-commssend a message to agent-2: ready to review the PR?"
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.
mcp-comms
MCP server for multi-agent communication. Multiple AI agents (Claude Code, Codex, etc.) working on the same codebase can coordinate via a shared SQLite-backed message log.
How it works
Each agent spawns its own server.py process over STDIO. All processes in a workspace share a single SQLite database, giving every agent a shared message bus with directed messages, broadcasts, and session discovery.
Agent A (claude-1) ──spawns──> server.py --name claude-1 ──┐
Agent B (codex-1) ──spawns──> server.py --name codex-1 ──┼──> <workspace>/.agent-comms/comms.db
Agent C (codex-2) ──spawns──> server.py --name codex-2 ──┘The DB path defaults to .agent-comms/comms.db relative to CWD, so each project gets its own message log.
Related MCP server: Brain MCP
Setup
Requires uv. No install step — uv run --script handles dependencies automatically via PEP 723 inline metadata.
Claude Code
Add to .mcp.json in your project:
{
"mcpServers": {
"comms": {
"command": "uv",
"args": ["run", "--script", "/path/to/mcp-comms/server.py", "--name", "claude-1"]
}
}
}Codex
Add to .codex/config.toml in your project:
[mcp_servers.comms]
command = "uv"
args = ["run", "--script", "/path/to/mcp-comms/server.py", "--name", "codex-1"]Replace /path/to/mcp-comms with the actual path where you cloned this repo. Give each agent a unique --name.
MCP Tools
Tool | Description |
| Send a directed message to a named session |
| Message all other sessions |
| Check inbox (marks messages as read) |
| Discover other agents |
| Lightweight unread count (doesn't mark as read) |
| Bidirectional history with another agent |
| Global message log (doesn't mark as read) |
CLI Options
uv run --script server.py --name <session-name> [--db-path <path>]--name(required): unique session name for this agent--db-path(optional): path to SQLite database (default:.agent-comms/comms.db)
Running Tests
uv run pytest tests/Design Notes
SQLite WAL mode for concurrent reads/writes across multiple agent processes
Thread-safe connections via
threading.local()Heartbeat tracking — every tool call updates
last_heartbeat, so agents can detect stale sessionsRead tracking — messages are marked read per-session via a JSON array, so each agent gets its own unread state
Broadcasts reach everyone except the sender
send_messagefails fast with a helpful error listing known sessions if the target doesn't existDelete
.agent-comms/comms.dbto reset all state
This server cannot be deployed
Maintenance
Related MCP Connectors
End-to-end encrypted messaging and work coordination for autonomous AI agents.
Persistent discussions, shared context and subscriptions for independently operated AI agents.
Durable agent-to-agent handoffs and shared scratchpad for multi-agent workflows.
Messaging and inboxes for AI agents: register, send signed messages, check your inbox, find agents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA SQLite-backed message queue system that enables multiple AI agents to communicate with each other via a simple HTTP interface.4Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables inter-session communication and coordination for multiple Claude Code instances through a shared SQLite database. Supports real-time messaging, shared state management, and resource locking to facilitate parallel development workflows between AI agents.9 npm8MIT
- AlicenseAqualityBmaintenanceEnables local messaging between Claude Code, Codex, Pi, and other coding-agent sessions on the same machine, allowing them to discover each other, send updates, ask questions, and reply.89 npm2AGPL 3.0
- AlicenseAqualityBmaintenanceEnables local AI coding agents to message each other on one machine using a durable SQLite mailbox and live-ask tools.9MIT