MCP server · Developer tools
Pincushion MCP server
by jcooley8
Let your AI read visual feedback pins from your live app and fix each one in your editor.
Pincushion is a tool where people drop little pins on a live web page to point out things that need fixing. This MCP server connects those pins to your AI coding assistant, so the AI can read each pin and make the change. It is handy if you build or maintain a web app and get feedback from designers, testers, or clients.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to another service. This one connects your AI to Pincushion, where the feedback pins live. Once it is connected, your AI can look up pins, read the details, and mark them as fixed when you ask.
What this MCP server does
You ask your AI to look at the feedback pins for your project. The AI uses this helper to reach Pincushion and pull the list of open pins. Each pin comes with the page address, the exact element on the page, a screenshot, a snippet of the page code, and the comment thread. Your AI reads all that, makes the code change in your editor, and can mark the pin as resolved with a note about what it did.
Click to zoomWhat you can do with it
- List all open feedback pins for your project
- Search pins by text, page, or component name
- Read the full details of a single pin, including screenshot and selector
- Reply to a pin thread to ask a clarifying question
- Mark a pin as resolved after fixing it, with a note
- Record the commit, branch, and pull request that fixed a pin
- Get a summary of how much feedback is open, in progress, or resolved
Try asking your AI
- “Show me all the open feedback pins for the checkout page”
- “Read the pin about the sign-in button label and fix it”
- “Search the pins for anything mentioning accessibility”
- “Resolve the pin I just fixed and note the file and line number”
What it gives back to you
You get back a list of pins with their page, status, priority, and the comment thread. For a single pin, you also see the element selector, a screenshot reference, and a snippet of the page code. When your AI resolves a pin, it can record the commit, branch, and pull request so the dashboard shows what shipped. Some tools return counts and simple summaries, like how many pins are open or how long fixes usually take.
Before you start
What you need
- A Pincushion account (the setup wizard signs you in)
- Node.js 22.22 or newer within Node 22, or Node 24
- A supported editor or AI coding tool like Claude Code, Cursor, VS Code, or Windsurf
Good to know
It can change the status of pins and write replies on your behalf, so review what your AI did before sharing the results with your team.
Install it with your AI
Add Pincushion MCP server to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check Pincushion MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.
Who it's for
Developers and small product teams who get visual feedback on a live web app and want their AI assistant to help work through it.
