How to create QR codes from Claude and ChatGPT with MCP A developer built qrlia, a QR code platform with a remote MCP server that connects Claude, Claude Code, ChatGPT and Cursor to QR code creation, dynamic redirect updates, scan analytics and saved brand designs. The server uses OAuth 2.1 with no API key, exposes read, write and opt-in admin scopes, and shares one service layer with a REST API documented via OpenAPI. The developer, who disclosed building the product, said the next step is tuning prompts based on user feedback. QR codes are a good fit for an AI assistant: the task is small, the input is a URL, and the output is an image. This tutorial connects Claude or ChatGPT to qrlia https://qrlia.com/mcp-gateway?utm source=devto&utm medium=community&utm campaign=mcp-launch , a QR code platform with a remote MCP server, and walks through creating, updating and tracking a code. Disclosure: I built qrlia. No API key is needed. The server uses OAuth 2.1: you sign in in the browser and approve access. https://mcp.qrlia.com/mcp qrlia.read , qrlia.write , and an opt-in qrlia.admin for workspace admins qrlia is in the Claude connector directory: https://claude.ai/directory/connectors/qrlia https://claude.ai/directory/connectors/qrlia In ChatGPT, open Settings → Apps, turn on developer mode under Advanced, and create an app with the URL https://mcp.qrlia.com/mcp . ChatGPT opens the qrlia sign-in; approve access. Your ChatGPT plan needs to support custom apps. claude mcp add --transport http qrlia https://mcp.qrlia.com/mcp Then, inside Claude Code: /mcp Select qrlia and sign in in the browser window that opens. Add --scope user to the add command if you want it in every project. Add the server to your client's MCP config. For Cursor ~/.cursor/mcp.json : { "mcpServers": { "qrlia": { "url": "https://mcp.qrlia.com/mcp" } } } Cursor will prompt you to sign in. Configs for other clients are in https://github.com/mgazelle/qrlia-mcp https://github.com/mgazelle/qrlia-mcp . Create a QR code for https://example.com called Spring flyer and show me the image. Claude calls a create tool, then fetches the image PNG or SVG and shows it. The code is dynamic: it encodes a short link, and the short link redirects to your URL. You printed 500 flyers and the page moved: Change the Spring flyer code to point to https://example.com/summer. The printed code stays the same. Only the redirect changes. Show scan analytics for the last 30 days: which codes were scanned most, and from which countries? On the free plan you get scan totals. Pro adds breakdowns by day, country, city, device, OS and referrer. On a paid plan you can describe your brand and let the assistant save it as a design: Save a design called Brand: dark red 7C220D modules, blue 00AEEF corner markers, rounded dots, our logo from https://example.com/logo.png in the centre, and a banner frame that says "Scan to save my contact". Then apply it to the Spring flyer code. Every code that uses the design follows it, and editing the design updates them all. Without your own logo, codes show the qrlia mark; you can also ask for no logo at all. The same operations are in a REST API with OpenAPI docs at https://docs.qrlia.com https://docs.qrlia.com Pro plan . MCP and REST share one service layer, so they behave the same. That's the whole setup: one URL, one sign-in. If you try it, tell me which prompts work badly; that's what I'm tuning next.