Skip to main content
JTL provides a Model Context Protocol (MCP) server that gives AI tools direct access to the full developer documentation. Once connected, the AI you already use can answer platform questions, write code, and reference current behaviour for any JTL product. The server URL is the same for every tool:

​
Connect Your AI Chat App

Use these steps if you work in ChatGPT or Claude. No terminal or config files are needed.
Connecting the JTL docs requires ChatGPT Developer mode, which is available on Plus, Pro, Business, Enterprise, and Edu plans on chatgpt.com. It is not available on the Free plan or in the ChatGPT mobile apps.
1

Turn on Developer mode

Open Settings > Apps > Advanced settings and turn on Developer mode. You only need to do this once.
2

Add the JTL docs

In Settings > Apps, click Create app next to Advanced settings. Enter JTL Docs as the name and paste the server URL:
Set Authentication to No Authentication, then create the app. It appears under Drafts in your app settings.
3

Turn it on in a chat

In a chat, click + in the message box, choose Developer mode, and select JTL Docs.
ChatGPT marks Developer mode as an elevated risk because it can connect to any MCP server. The JTL docs server only searches and reads the documentation, and can send feedback about a page to the JTL documentation team. ChatGPT may ask you to confirm before it sends feedback. It has no access to your ChatGPT or JTL accounts.

​
Connect your Coding Tool

Use these steps if you build in an editor or terminal.
Add the JTL docs MCP server with a single command:
Restart Claude Code, then run /mcp. You’ll see jtl-docs · ✔ connected as part of the MCP servers.
You can also connect directly from any page in these docs. Click the contextual menu (top of any page) and select Connect to Cursor or Connect to VS Code to add the MCP server with one click.

​
Check That It Works

Ask one of these questions after connecting. When the connection works, the response shows a call to the JTL docs tool before the answer.
  • “What is a JTL Cloud App, and where does it appear for merchants in JTL ERP Cloud?”
  • “Walk me through building my first JTL Cloud App from the template, step by step.”
  • “How does my Cloud App know which merchant is using it?”
  • “What do I need to prepare before submitting my Cloud App to the JTL App Store?”
If the answer does not show a tool call, check that the JTL docs are turned on for the current chat. In ChatGPT, it also helps to name the app in your question, for example “Use JTL Docs to explain what a JTL Cloud App is.”

​
Other Ways to Use the Docs

These options work without any setup and are useful for one-off questions or tools that don’t support MCP. Copy as Markdown. On any page, press Cmd+C / Ctrl+C or select Copy from the contextual menu to copy the page content as Markdown. Paste it directly into ChatGPT, Claude, or any other AI tool. Claude and ChatGPT links. Select Open in Claude or Open in ChatGPT from the contextual menu on any page. This opens the AI tool with the page content pre-loaded. llms.txt. The docs site hosts an llms.txt file listing every page with a short description. AI crawlers use it to index the documentation, and you can fetch it directly to give a tool an overview of what is available.

​
Tips for Better Results

These apply regardless of which product you build against. Name the product. “How do I authenticate?” is ambiguous across products with different authentication models. “How do I authenticate a Cloud App backend?” retrieves the right page. Be specific about what you’re building. “Help me build a JTL Cloud App” is vague. “Create a panel app that shows customer order history in the customer sidebar” gives the tool enough context to generate accurate code. Use JTL terms. Words like Cloud App, AppBridge, session token, and App Store map directly to documentation pages, so the tool finds the right answer faster. Ask the tool to check its work. After it writes code, ask “Check this against the JTL docs. Is anything missing or outdated?” and it will compare its answer with the current documentation. Combine with the quickstarts. Start with From Template or From Scratch to get a running app, then use AI to extend it.

​
What’s Next

Quickstart: From Template

Clone the sample app and get a running Cloud App in 15 minutes.

Quickstart: From Scratch

Build a Cloud App step by step with React and your favourite backend (Node.js, C#, or PHP).

Marketplace Channels

Connect a marketplace to JTL-Wawi through SCX.

Vouchers API

Issue and manage vouchers through the Vouchers API.