---
title: "Goose ACP Setup | AgentRQ Docs"
url: https://agentrq.com/docs/agents/goose
description: "Goose ACP setup: run Goose over the Agent Client Protocol and connect it to AgentRQ for human-in-the-loop task management."
---

[Docs](https://agentrq.com/docs/) / Agents / Integrations

Integrations

# Goose ACP Setup

Goose ACP setup: run Goose over the Agent Client Protocol and connect it to AgentRQ for human-in-the-loop task management.

[Goose](https://block.github.io/goose/docs/guides/acp-clients) is Block's open-source, extensible AI agent. It supports connecting to ACP clients, so it can be bridged to AgentRQ with no custom integration code.

Wondering which other coding agents support ACP? See the [ACP support table](https://agentrq.com/blog/which-coding-agents-support-acp-agent-client-protocol) for 33 agents.

Want Goose to use websites too? [Connect Goose to WebMCP](https://agentrq.com/docs/webmcp/goose) shows how it can call a site's WebMCP tools in your own Chrome.

## Does Goose Support ACP?

Yes. Goose publishes an ACP server to the [ACP registry](https://github.com/agentclientprotocol/registry) as `goose`, 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 Goose is bridged through AgentRQ's [ACP Gateway](https://agentrq.com/docs/connect-acp-agent), every task it works on shows up on your AgentRQ [task board](https://agentrq.com/features/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 Goose is running in.

## Connect Goose

Run both commands from your project root — the directory holding your `.mcp.json`.

Log in (the first run also downloads the agent):

bash

```bash
npx @agentrq/acp-gateway@latest --login --agent goose
```

Start the bridge, and leave it running — it picks up tasks as you assign them:

bash

```bash
npx @agentrq/acp-gateway@latest --agent goose
```

That `.mcp.json` is what tells the gateway which workspace to take tasks from:

json

```json
{
  "mcpServers": {
    "agentrq": {
      "type": "http",
      "url": "https://WORKSPACE_ID.mcp.agentrq.com/mcp?token=TOKEN"
    }
  }
}
```

See the [ACP Gateway guide](https://agentrq.com/docs/connect-acp-agent) for the full setup walkthrough, including where to find your Workspace ID and token.

## FAQ

**Does Goose work with AgentRQ?**

Yes — Goose is listed as an ACP-compatible agent, so it connects to AgentRQ through the open-source [ACP Gateway](https://agentrq.com/docs/connect-acp-agent) with no custom integration code.

**How do I connect Goose to AgentRQ?**

Run `npx @agentrq/acp-gateway@latest --login --agent goose` from your project root, then start the bridge with the same command minus `--login`. A `.mcp.json` there points the gateway 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 Goose — can use AgentRQ as its human-in-the-loop task manager.

## References

- → [Which coding agents support ACP?](https://agentrq.com/blog/which-coding-agents-support-acp-agent-client-protocol)
- → [Goose ACP clients guide](https://block.github.io/goose/docs/guides/acp-clients)
- → [Agent Client Protocol specification](https://agentclientprotocol.com)
- → [AgentRQ ACP Gateway guide](https://agentrq.com/docs/connect-acp-agent)
- → [Connect Goose to WebMCP](https://agentrq.com/docs/webmcp/goose)