$ loading_
Automate Chrome browser actions with stable element targeting.
This is an open-source, MIT-licensed browser automation MCP. The materials show no required credentials and no declared fixed remote endpoints, with no clear high-risk red flags; however, it does execute locally and can automate a browser, so it may access current browsing content and page data and is best used in a constrained environment.
The materials explicitly state that no keys or environment variables are required. No API keys, account tokens, or other sensitive credentials are requested, so credential exposure appears limited.
No fixed remote endpoint is declared, but the tool automates Chrome; in practice, the browser may visit user-specified sites and expose page content within the tool workflow. The materials do not show a red flag of extra exfiltration to unrelated third-party services, but normal network egress through browsing activity should be expected.
The system flags executes-code, and the description indicates it is an MCP server that directly controls Chrome via CDP, implying local process launch/control and browser automation actions. This is a normal but privileged capability for this tool category and warrants runtime isolation.
The description shows it uses CDP and the accessibility tree for element selection, so it can reasonably access browser page content, DOM/accessibility-tree data, and related session information. The materials do not indicate requests for broad local file or system permissions beyond browser automation needs, and no clear over-privilege is evident.
Positive factors include being open source, auditable, and MIT-licensed, which lowers risk. However, it comes from a third-party registry, has only 0 stars, unknown maintenance status, and sparse documentation, so supply-chain confidence is limited though not high-risk.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "Public Browser" yet — see the docs or source repo.
Use Public Browser to open a website, log in, click menus, fill out a form, and submit it; prefer accessibility-tree-based element targeting over fragile CSS selectors.
An executable browser automation flow or a result summary.
Use Public Browser to run a smoke test on this page: open it, verify key buttons are clickable, confirm form submission succeeds, and record any failed steps.
Test steps, pass/fail status, and issue location.
Use Public Browser to visit multiple pages and extract titles, prices, and summaries, minimizing breakage from layout changes with CDP and stable references.
A structured table or extracted data set.
Automate browsers and manage bookmarks across major browsers from one MCP tool.
Automate browser tasks, capture console logs, and take screenshots for web workflows.
Let AI control a real browser for navigation, forms, and web tasks.
Control a browser with AI for automation, extraction, interception, and screenshots.
Control a real local browser for web automation, extraction, and screenshots.
Let AI browse via your real Chrome for extraction and multi-step workflows.