Invisible Playwright MCP AI Agent
Playwright MCP server undetected by anti-bots and captchas: AI agent browses the web on anti-detect stealth Firefox, Python, undetected browser automation, scraping, computer use.
Invisible Playwright MCP is an open-source ai agent by feder-cr, written mainly in Python, with 888 GitHub stars and the MIT license. Its code was last updated Oct 21, 2026.
Scan summary: scanned Nov 5, 2026 at commit 0df2a15. Seen able to run dynamic code, read environment and secrets, control a web browser, connect to the internet. Scan policy
0df2a15 · Nov 5, 2026Findings (8)
- highHigh. Something risky that needs a close look before you install.dropper issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.dropper issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.dropper issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.dropper issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.dropper issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.network issueDetails are available to the maintainer after claiming this listing.
- lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
tests/test_cli_surface.py:31 - lowLow. Minor, or common in normal tools. Shown for information.Reads environment variables not listed in the manifestGITHUB_REPOSITORY, GITHUB_TOKEN, GH_TOKEN, STEALTHFOX_MCP_TRANSPORT, STEALTHFOX_MCP_HOST, STEALTHFOX_MCP_PORT, APPDATA, XDG_DATA_HOME
Network activity
Tools exposed (17)
browser_openOpen `main` or `support`, or reopen one as somebody else. `support` is yours to manage: open it when the task needs a second identity, and close it with browser_close as soon as the task no longer needs it, before you answer. It is not saved. Called on a browser that is already up,
browser_closeClose one browser and free what it was holding. The page it had is gone with it. The other browser is not touched. Who it was is kept: browser_open with no arguments brings the same person back. To be somebody else, pass a seed, a proxy or a profile.
browser_listWhich of the two browsers are open, where each one is, and which one you are working in. Answers JSON: `focus`, the browser your last command acted in, or "" when none is open; `note`, which says how many are open and that a command naming no browser goes to `main`; and `browsers` -
browser_statusWho is browsing right now: the identity, the exit, the profile and the page. Ask whenever you need to know which person the browser currently is, or from where its traffic leaves. The seed is what you would pass to `browser_open` to become this person again, so this is also how you
browser_navigateGo to a url in this browser's page, opening it if none exists. Answers with the HTTP status the server gave and the url actually landed on, which is not always the one asked for: a redirect to a login wall or a regional domain shows up here. Read the status before trusting the page -
browser_read_textThe visible text of an element, with the markup gone, whole. The cheapest way to read a page. Narrow the selector when you know where the answer is; use browser_read_html instead when the structure matters, or browser_snapshot when you need something to click.
browser_snapshotTitle, url, and the interactive elements that are actually visible. Each element carries a `selector` when one can reach it: pass that string to browser_click or browser_type VERBATIM rather than writing your own. It is built to match exactly ONE element, which the obvious selector ofte
browser_read_htmlThe page's HTML, cleaned down to what is worth reading. Use this when the STRUCTURE matters - a form and its labels, a table, what a control is wired to. `browser_snapshot` gives a flat inventory of things to click; this keeps the markup and the relationships inside it. mode="form"
browser_take_screenshotOne screenshot of this browser's page, on demand.
browser_watchThe whole browser window as a person at the machine sees it: tab strip, address bar, the page and the pointer, from a live capture kept running on that page. For watching the work, not for acting on it: the picture is window pixels, so do not feed its coordinates to browser_click_at; use
browser_clickClick the first element matching a CSS selector. Scrolls it into view and waits for it to be clickable. When no selector can describe the target, use browser_click_at with coordinates from browser_snapshot.
browser_click_atClick (or press-and-hold) a raw viewport coordinate instead of a selector - for targets a selector cannot reliably reach: a slider track, a canvas-drawn captcha, a precise point inside a wider element. Moves the pointer there first (no teleport), then down, then up, holding first if
browser_typeType into a field, replacing what it holds, key by key at a human pace. The answer says what the field kept: all of it, a maxlength's cut, the page's reformatting, nothing (the page took it out), or one box of a code the page spreads over several. Nothing is retyped on its own. Text too
browser_select_optionChoose an option in a dropdown (`<select>`), by its visible label or by its value. Use this rather than clicking the dropdown and pressing arrow keys: a click plus arrows cannot tell you which row it landed on, and setting the value through browser_evaluate changes it without the pa
browser_upload_filesAttach local files to a file input, the way a person picks them. `selector` is the `<input type=file>` itself, or the button or label that opens its chooser: that is clicked with the real pointer and the chooser answered with `paths`. A hidden input is opened through its label; with
browser_press_keyPress a key on whatever has focus: "Enter", "Tab", "Escape", "ArrowDown", "Control+a", or a single character.
browser_evaluateREAD from the page with JavaScript and get the result as JSON. Last, for what other tools cannot see: a computed style, a value held in a framework's state, the length of a list. Text, a heading or a price is browser_read_text's, markup browser_read_html's, a control browser_snapsho
Automated result for the commit shown. See our scan policy. View the scan log
Maintainers can claim the listing to rescan, or dispute a result.
Invisible Playwright MCP alternatives
View more →Similar ai agents in Browser Automation, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.
| Name | Stars | Licence | Last updated | Scan |
|---|---|---|---|---|
| Invisible Playwright MCP (this page) feder-cr | 888 | MIT | Oct 21, 2026 | Scanned, no flagged issues |
| Browser Use browser-use | 120k | MIT | Oct 31, 2026 | Scanned, no flagged issues |
| CloakBrowser CloakHQ | 33k | MIT | Oct 31, 2026 | Scanned, no flagged issues |
| Invisible Dots feder-cr | 32k | MIT | Oct 31, 2026 | Scanned, no flagged issues |
| OpenCLI jackwener | 31k | Apache-2.0 | Oct 26, 2026 | Scanned, no flagged issues |
| Stagehand browserbase | 26k | MIT | Oct 30, 2026 | Scanned, no flagged issues |