Human-in-the-Loop Task Manager for AI Agents
Docs / Agents / Integrations
Integrations

Connect localharness to AgentRQ

Connect localharness to AgentRQ over the Agent Client Protocol (ACP) for human-in-the-loop task management.

localharness is a local agent testing harness listed as ACP-compatible, so it can run behind AgentRQ's gateway with no custom integration code.

Does localharness Support ACP?

Yes. Check localharness's repository for the exact command that starts it in ACP server mode.

What Connecting via ACP Gets You

Once localharness 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 localharness is running in.

Connect localharness

Once you have localharness's ACP command from its docs, wrap it with AgentRQ's gateway:

bash 
npx @agentrq/acp-gateway@latest -- <localharness-acp-command>

Then point it at your workspace with a .mcp.json in your project root:

json 
{
  "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 localharness work with AgentRQ?

Yes — localharness is listed as an ACP-compatible agent, so it connects to AgentRQ through the open-source ACP Gateway with no custom integration code.

How do I connect localharness to AgentRQ?

Find localharness's ACP launch command in its official docs, then run npx @agentrq/acp-gateway@latest -- 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 localharness — can use AgentRQ as its human-in-the-loop task manager.

References