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

Connect Cortex Code to AgentRQ

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

Cortex Code is Snowflake's coding agent. It speaks the Agent Client Protocol (ACP), so it runs behind AgentRQ's gateway with no custom integration code.

Does Cortex Code Support ACP?

Yes. Cortex Code publishes an ACP server to the ACP registry as cortex-code, 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 Cortex Code 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 Cortex Code is running in.

Connect Cortex Code

Copy the .mcp.json for your workspace from Settings → Setup in the AgentRQ app, save it in your project root, then run both commands from that directory.

The registry publishes no sha256 for Cortex Code, and the gateway will not install a download it cannot verify. --allow-unverified-agent is you accepting that trade-off, and it belongs on every command.

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

bash 
npx @agentrq/acp-gateway@latest --login --agent cortex-code --allow-unverified-agent

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

bash 
npx @agentrq/acp-gateway@latest --agent cortex-code --allow-unverified-agent

Cortex Code ships as a prebuilt binary, which the gateway downloads, checks and caches per agent, version and platform.

Choosing a Model

Ask Cortex Code which models it supports, then start it on one of them:

bash 
npx @agentrq/acp-gateway@latest --list-models --agent cortex-code --allow-unverified-agent
npx @agentrq/acp-gateway@latest --model <model-id> --agent cortex-code --allow-unverified-agent

Omit --model to take whatever the agent defaults to. The gateway applies the model as each session opens and reports it back to AgentRQ, so the workspace shows which model actually ran.

FAQ

Does Cortex Code work with AgentRQ?

Yes — Cortex Code 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 Cortex Code to AgentRQ?

Save your workspace's .mcp.json in your project root, log in with npx @agentrq/acp-gateway@latest --login --agent cortex-code --allow-unverified-agent, then start the bridge with the same command minus --login.

Why does Cortex Code need --allow-unverified-agent?

The ACP registry publishes no checksum for the Cortex Code binary, and the AgentRQ gateway will not install a download it cannot verify. The flag is required on every command, and only the first run downloads anything.

References