Connect Kimi CLI to AgentRQ
Connect Kimi CLI to AgentRQ over the Agent Client Protocol (ACP) for human-in-the-loop task management.
Kimi CLI is Moonshot AI's terminal coding agent. It supports the Agent Client Protocol (ACP), so it can run behind AgentRQ's gateway with no custom integration code.
Does Kimi CLI Support ACP?
Yes. Kimi CLI publishes an ACP server to the ACP registry as kimi, so AgentRQ's gateway can fetch and run it by name — there is nothing to install by hand.
What Connecting via ACP Gets You
Once Kimi CLI is bridged through AgentRQ's ACP Gateway, every task it works on shows up on your AgentRQ task board in real time. You can approve risky commands, reply with extra context, or reassign work — from the dashboard or Slack — without touching the terminal Kimi CLI is running in.
Connect Kimi CLI
Run both commands from your project root — the directory holding your .mcp.json.
Log in (the first run also downloads the agent):
npx @agentrq/acp-gateway@latest --login --agent kimi
Start the bridge, and leave it running — it picks up tasks as you assign them:
npx @agentrq/acp-gateway@latest --agent kimi
That .mcp.json is what tells the gateway which workspace to take tasks from:
{
"mcpServers": {
"agentrq": {
"type": "http",
"url": "https://WORKSPACE_ID.mcp.agentrq.com/mcp?token=TOKEN"
}
}
}
See the ACP Gateway guide for the full setup walkthrough, including where to find your Workspace ID and token.
FAQ
Does Kimi CLI work with AgentRQ?
Yes — Kimi CLI speaks the Agent Client Protocol (ACP), so it connects to AgentRQ through the open-source ACP Gateway with no custom integration code.
How do I connect Kimi CLI to AgentRQ?
Run npx @agentrq/acp-gateway@latest --agent kimi from your project root, with a .mcp.json pointing at your AgentRQ workspace.
What is the Agent Client Protocol (ACP)?
ACP is an open, editor-agnostic protocol that lets any coding agent talk to any client over a standard JSON-RPC interface. AgentRQ's gateway implements the client side of ACP, so any ACP-compatible agent — including Kimi CLI — can use AgentRQ as its human-in-the-loop task manager.