DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to have Claude draft site changes over MCP for approval with Kaletacms

Connect Claude to your Kaleta site so it drafts pages, site parts and design changes you review before publishing.

Credentials. Giving Claude MCP access to a live admin means it can change the site, so use an account with limited rights and keep changes in draft until you approve them.

Who it is forA web agency or site owner who already uses Claude and wants it to build sections from existing HTML or edit site content without publishing unreviewed changes.

The problemTurning existing HTML or design notes into builder content by hand is slow, and direct AI edits to a live site are risky.

The outcomeClaude-created changes appear as drafts in the site, ready for review and approval.

What you need first

  • Hosting with PHP 8.3 or newer and MySQL 8 or MariaDB 10.6 or newer
  • FTP access to the hosting and a way to create an empty database
  • The kaleta-X.Y.Z.zip file from the GitHub Releases page

Steps

  1. Install Kaleta and finish the setup in the admin, as in the launch use case.
  2. Connect Claude to the site over MCP, following the setup steps in the user guide at Kaletacms.com/guide.
  3. Ask Claude to convert a block of HTML into builder content, or to edit site parts, collections or the design.
  4. Open the admin, review each draft and approve it before it goes live.

Prompt for your agent

Using the kaletacms repository and its MCP support, ask Claude to convert the HTML in <source-file> into a draft page on my Kaleta site at <site-url>. Expected output: the draft's name and a list of changed elements, and confirm nothing is published until I approve it.

Caveat. The README says Claude changes are always drafts to approve, but it does not describe the MCP connection steps, so check the user guide for the exact setup.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page