Skip to main content
Connect Replo to Cursor, Claude Code, or your coding client, then ask it to open your site locally. Use your own AI plan to make edits and see them in a live preview. When a change is ready, your coding client pushes it to Replo. Anything on main goes live with the next publish, so keep unfinished work on a branch.

​
Start here

Connect the Replo MCP server, open a local workspace, and paste this prompt with your project name:
The setup checklist for coding clients and Git authentication reference below cover the steps your client needs to complete this request. Your client handles the clone and setup. You need Git, Node.js, and pnpm on your computer. If it cannot open a browser, open the local URL it gives you.

​
Try an edit

Once the preview is running, ask for a change. For example:
Check the result in the browser, then keep refining in the same chat. Local coding uses your coding client’s plan; work requested inside Replo uses applicable Replo credits.

​
Keep Replo in sync

When a change is ready, ask your coding client to check it and push it to main. Anything on main goes live with the next publish of the site, even a one-page publish, so keep unfinished work on a local branch. Review the draft in Replo whenever you need to. Publishing is a separate action that makes the changes live.

​
Setup checklist for coding clients

When a user gives you this page to set up a site, complete these steps. The Git authentication reference contains the credential setup and commands; read it before cloning.
  1. Find the workspace. Use list_projects if you do not already know its ID.
  2. Connect git. Read the local-development skill with skills({ name: "local-development" }) and follow its setup: it reuses a working stored credential, otherwise calls create_api_key with type: "user" for a user API key and gets the site’s clone_url from list_sites, stores the credential with git’s credential helper, and verifies it. Never print the password, put it in a URL or command line, or commit it.
  3. Clone into a new folder. Verify access with git ls-remote, then clone the returned URL. Run subsequent commands from that checkout. If it already exists, inspect its remote and local changes before using it; preserve existing work.
  4. Read the skills for the task. Call skills with no arguments to list every skill, then load the ones the request needs, one call each, starting with building-replo-pages for page edits. See Agent skills.
  5. Install and start. Read the checkout’s instructions, package.json, package-manager configuration, and lockfile. Use their required Node.js and package-manager versions. If the checkout does not declare versions, use the supported Node.js 22 and pnpm 10 fallback in local SDK setup. Install dependencies and start the declared development script. Most Replo sites use pnpm install and pnpm dev. Keep credentials and machine-specific configuration out of commits.
  6. Verify the preview. Check the actual URL reported by the server and load the requested page. Confirm it renders the site, then open it in the user’s browser. A rendered route does not by itself prove that product data loaded successfully. When product data is expected, verify it against active products and confirm the expected data appears; an empty fixture or one with only inactive products leaves product loading unproven. If browser access is unavailable, provide the exact local URL. Keep the server running. Report a failed clone, install, skills check, or preview instead of claiming setup is complete; use Git troubleshooting for recovery.
Push only when the user says a change is ready: fetch and reconcile newer Replo changes without discarding local work, run the site’s checks, then push. Never force-push. Report a failed check or push instead of claiming the draft is updated. Publish only when requested. Need help? Troubleshoot Git.