Human-in-the-Loop Task Manager for AI Agents
Checked November 14, 2026 | All Connect Agents guides

Connect Claude Code with Machines

To connect Claude Code to an AgentRQ workspace, enrol the computer that should run it as a machine, then click Start an agent in the workspace, pick Claude Code, choose its model, effort and auto-compact window, and start it. AgentRQ starts Claude Code on that machine and shows its live terminal in the browser, so you can answer its first-run questions and approve its tool calls without opening a terminal yourself. This guide shows every click, with Opus 5.5 at High effort, and ends with a first task done end to end. If you would rather not enrol a machine, the last section runs the same thing from your own terminal.

This page is one of our connect agents guidelines. For Antigravity, Gemini CLI, Codex and other ACP agents, see Connect Agents with the ACP Gateway and Machines. It was checked against AgentRQ and Claude Code 2.1.325 on November 14, 2026, and every screenshot below comes from a real run.

How Claude Code Gets Its Tasks

Claude Code talks to AgentRQ over the workspace's MCP server, and it receives tasks through a channel: a message from that server that lands in the running session as if you had typed it. When you start Claude Code from AgentRQ, the machine's daemon does three things before it runs Claude Code:

  • → It writes the workspace's .mcp.json into the working directory, and in a git checkout adds that file to .gitignore, because it holds the workspace token.
  • → It writes .claude/settings.local.json, which allows every tool of the AgentRQ server, so Claude Code does not stop and ask before each task update. Rules you already have in that file are kept.
  • → It starts Claude Code with the channel turned on, using the model, effort and auto-compact window you picked.

Claude Code still asks before it runs a shell command or edits a file, unless you change that. You answer those prompts in the terminal AgentRQ shows you, or in the task itself.

Before You Start

  • → An AgentRQ workspace with a working directory set in its General settings. That folder is where Claude Code runs on the machine. The example workspace is storefront-api.
  • → A computer with Claude Code installed and signed in. Run claude once on it if it never has been.

Step by Step: Enrol the Machine

Skip to step 5 if the machine is already enrolled and online.

1. Open Machines in the sidebar.

Step 1: an AgentRQ workspace, with an arrow pointing at the Machines icon in the left sidebar

2. Click + Add machine.

Step 2: the empty Machines page, with an arrow pointing at the + Add machine button at the top right

3. Run both commands on the machine that will run Claude Code. The first installs agentrqd, the small AgentRQ daemon. The second enrols it with a one-time code and starts it in the background. Pick the Linux, macOS or Windows tab to match the machine.

Step 3: the Add a machine panel with the install command and the agentrqd enroll command, both highlighted
bash
curl -fsSL https://agentrq.com/install-agentrqd.sh | sh
agentrqd enroll --server https://app.agentrq.com --code ABCD-EFGH

Run it as the user who signed in to Claude Code, never as root: agentrqd refuses to run as root, and Claude Code runs with that user's login and rights. The machines and daemon docs cover what enrolling allows, how to keep agentrqd running as a service, and how to undo it.

4. Check that the machine is online. It appears on the Machines page with a green dot.

Step 4: the Machines page listing dev-laptop with a green online dot, highlighted

Step by Step: Start Claude Code on Opus 5.5

5. Click Start an agent in your workspace. An offline workspace offers it in the middle of the page while a machine is online. The same card sits at the top of Settings → Setup.

Step 5: the storefront-api workspace, still offline, with an arrow pointing at the Start an agent button

6. Under What to run, pick Claude Code. The card also says which folder and which machine Claude Code will run in.

Step 6: the Start an agent card, with an arrow pointing at the Claude Code option under What to run

7. Slide Model to Opus 5.5. The steps are the models the machine's own Claude Code reports, here Haiku 5.5, Sonnet 5.5, Opus 5.5 and Fable 5.2. Default leaves the choice to Claude Code, and its label says which model that is.

Step 7: the Model slider moved to Opus 5.5, highlighted

8. Slide Effort to High. The steps are Default, Low, Medium, High, Extra high and Max, the levels claude --effort accepts.

Step 8: the Effort slider moved to High, highlighted

9. Leave Auto-compact at 400k, or move it. It sets how much context Claude Code holds before it summarises the conversation, from 100k to 900k tokens.

Step 9: the Auto-compact slider at 400k (default), highlighted

10. Click Start an agent.

Step 10: the filled-in card with Claude Code, Opus 5.5 and High effort, with an arrow pointing at the Start an agent button

AgentRQ opens Claude Code's live terminal, with a Stop button. On the machine, agentrqd runs:

bash
claude --name storefront-api --model opus --effort high --autocompact 400k \
  --dangerously-load-development-channels server:agentrq-workspace

Answer Claude Code's First Questions in the Terminal

The terminal in AgentRQ is the real one. Click into it and use the arrow keys and Enter, exactly as you would at the machine.

11. Trust the folder. The first time Claude Code runs in a folder, it asks whether you trust it, and lists the tool permission AgentRQ pre-approved in .claude/settings.local.json. Pick Yes, I trust this folder and press Enter. Claude Code remembers the answer for that folder.

Step 11: Claude Code's trust prompt in the AgentRQ terminal, with

12. Confirm the channel. Claude Code warns that --dangerously-load-development-channels is for development channels. That flag is what lets the AgentRQ server deliver tasks into the session, so keep I am using this for local development and press Enter. Claude Code asks this on every start.

Step 12: the development channels warning, with

13. Check that Claude Code is listening. Its header shows the model and effort you picked, and a line says channel messages from server:agentrq-workspace go straight into the session.

Step 13: Claude Code started on Opus 5.5 with high effort, with the Channels line highlighted

14. Check that the workspace is connected. Back in the workspace, the dot next to its name turns green, and the terminal icon in the toolbar lights up.

Step 14: the storefront-api workspace with a green dot next to its name, highlighted

Run a First Task

15. Create a task. Click New Task, write what you want, and send it. The example asks for a README.

Step 15: the New Task form with

16. Answer Claude Code in the task. The example folder was empty, so instead of inventing a stack, Claude Code asked which way to go and set the task to blocked. Reply in the task, from the web, your phone or Slack.

Step 16: the task with Claude Code's question and the reply

17. Open the Agent terminal from the toolbar to watch Claude Code work.

Step 17: the task page, with an arrow pointing at the Agent terminal icon in the toolbar

18. Approve the edit in the terminal. Claude Code shows the file it wants to create and asks before writing it. Pick 1. Yes and press Enter. Option 2 approves file edits for the rest of the session. The same request also appears in the task with Allow Once, Always Allow and Deny, so you can answer from either place.

Step 18: Claude Code asking

19. Read the result. Claude Code writes the file, reports what it did in the task, and marks the task completed.

Step 19: the completed task with Claude Code's summary of the README it wrote, highlighted

Run Claude Code From Your Own Terminal Instead

No daemon, no enrolment: you start Claude Code yourself in the project folder.

1. Open the workspace Settings with the gear at the top right.

Option 2, step 1: the workspace page, with an arrow pointing at the Settings gear at the top right

2. Under Setup → Claude, click Copy Config and save it as .mcp.json in your project folder. It holds the workspace's MCP URL and its token, so keep it out of git. If it ever leaks, reset the workspace ID.

Option 2, step 2: the Claude tab of Setup with the .mcp.json masked, with an arrow pointing at Copy Config

3. Copy the Claude permissions and save them as .claude/settings.local.json in the same folder, so Claude Code calls the workspace's tools without asking each time.

Option 2, step 3: the settings.local.json block, with an arrow pointing at its Copy Config button

4. Copy the start command and run it in that folder. Add --model and --effort for Opus 5.5 at high effort:

Option 2, step 4: the Start command block, with an arrow pointing at its Copy button
bash
claude --dangerously-load-development-channels server:agentrq-<workspace-id> \
  --name storefront-api --model opus --effort high

Claude Code asks the same two questions as in steps 11 and 12. Once you answer them, the workspace's dot turns green. Leave the terminal open: the agent runs only as long as it does. The Claude Code setup docs cover the rest of this route: project or global config, the CLAUDE.md instructions that shape how Claude uses AgentRQ, and troubleshooting.

Machine vs Terminal at a Glance

On an enrolled machine From your own terminal
Install agentrqd, once Nothing beyond Claude Code
Config files Written for you Copy .mcp.json and settings.local.json
Start and stop From AgentRQ, any browser In that terminal
Answer prompts Terminal in AgentRQ, or the task That terminal, or the task
Model, effort, auto-compact Sliders in the Start an agent card --model, --effort, --autocompact
Best for Claude Code you run every day A quick try, or a one-off

FAQ

Why does Claude Code need --dangerously-load-development-channels?

Channels are how a running Claude Code session receives messages from an MCP server, and AgentRQ's server is loaded as a development channel. Without the flag, Claude Code starts and connects but never receives a task. The flag loads only the channel named after it, server:agentrq-workspace.

Do I have to click through the prompts every time?

The folder trust question comes once per folder. The channel confirmation comes on every start, so when you start Claude Code from AgentRQ, open the terminal and press Enter once.

Can Claude Code work without asking me before each command?

Yes. Approve with Always Allow in a task, pick the auto-approve option in the terminal, or set your own rules in .claude/settings.local.json. The YOLO mode guidelines for Claude Code cover each option and its risks.

The workspace went offline but Claude Code is still running. What now?

Claude Code lost its connection to the workspace's MCP server. Click the terminal icon in the workspace toolbar, type /mcp, pick agentrq-workspace and choose Reconnect. Fix a Disconnected AgentRQ MCP in Claude Code shows every click.

Can I stop Claude Code from AgentRQ?

Yes. Click Stop on its terminal page. The workspace goes offline, and Start an agent comes back so you can start it again with other settings.

Start Free