$ loading_
Control webpages with numbered element markers for AI-driven browser automation.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "browsercontrol" yet — see the docs or source repo.
After opening the target webpage, read the numbered markers, click the button labeled 3, and tell me what changed on the page.
Clicks the specified numbered element and reports the resulting page change or new state.
Identify the numbered markers on the login page, fill in the provided credentials in the username and password fields by their numbers, then click the submit button number.
Locates fields and buttons by number, then completes form filling and submission.
Browse the current webpage, first click navigation item 5, then click link 2 on the new page, and summarize which page each step opened.
Performs multiple webpage actions by number and returns a summary of the navigation path.
Developers building web agents can use numbered markers on interactive elements so the model does not rely on vague visual descriptions for clicking or typing. This makes webpage actions easier to break into explicit steps.
When product teams or researchers need AI to browse pages, open links, or submit forms step by step, element numbers provide clearer action instructions. It is suitable for web tasks that require multi-step navigation.
When testing web interaction flows, teams can have AI trigger page controls in sequence by number and observe navigation and state changes. It is better suited to scenarios focused on interaction steps rather than hand-written selectors.
It is an MCP server for browser automation. Its key idea is to annotate interactive webpage elements with numbered markers so AI can control the page by referencing those numbers.
Based on the description, it uses a vision-first approach and numbered markers for interactive elements. Compared with relying only on text descriptions or selectors, this makes it easier for AI to point to specific page elements.
The provided material does not include installation steps or prerequisite details. See the source repository.
Let AI control browsers for web automation, testing, inspection, and capture
Control a real local browser for web automation, extraction, and screenshots.
Control a browser through MCP for web actions, form filling, and screenshots
Automate browser navigation, interaction, and web data extraction for online tasks.
Automate browser tasks, capture console logs, and take screenshots for web workflows.
Let AI control a browser for web tasks, extraction, and testing.