Browser Agent MCP server

This is a helper that gives your AI its own web browser. You ask in plain words, and it opens pages, clicks buttons, types into forms and takes screenshots. It is handy if you often copy information from websites or repeat the same clicks and form filling by hand.

What this MCP server does

You tell your AI what you want in normal words, like going to a page or filling in a form. Your AI sends that instruction to this helper program running on your computer. The helper opens a browser window and performs the steps, one by one. It can also send web requests to fetch data and read the reply. Then it reports back what happened, plus screenshots or logs if you want them.

Click to zoom

What you can do with it

• Open any web page and wait for it to load
• Click buttons, links and menu items
• Fill in text fields and choose options from dropdowns
• Take screenshots of a full page or a single element
• Run small scripts inside the page to read values
• Send web requests to fetch or update data
• Read the browser console logs when something goes wrong

Try asking your AI

• “Go to https://www.google.com and take a screenshot named google-homepage”
• “Open https://the-internet.herokuapp.com/login, fill in the username and password, then click the login button”
• “Navigate to https://the-internet.herokuapp.com/dropdown and select Option 1 from the dropdown”
• “Fetch the data at https://jsonplaceholder.typicode.com/posts/1 and show me the result”

What it gives back to you

You get short answers in the chat, like what page it opened or what it clicked. Screenshots come back as saved files you can open, and you can ask for them by name. It can also show the browser's console logs and the data it fetched from a web request. If something failed, it tells you what went wrong so you can try again.

Before you start

Who it's for

Office workers who often copy information from websites, fill in the same online forms, or check pages by hand.