mcp-browser-extension
Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.
Needs to start: nothing
Returns a result when called with no setup: 0 of 5 tools tried
Contacts while installing and starting: us.i.posthog.com
What it contacted
us.i.posthog.com: usually analytics or error reporting
Hosts it looked up or connected to while installing and starting with no input, watched from outside its sandbox. The npm registry is left out. Says nothing about what its tools contact when called.
Starting it
npx -y mcp-browser-extension@0.9.40
Installing a package runs its code. Use a sandbox for anything you have not read.
Calling its tools
5 tools that take no input and look read-only were called once with nothing. 0 returned a result.
tabs_list | No usable answer tool reported an error: [ACCESS_INPUT_REQUIRED] Complete email verification in the browser form. It opens automatically when the client does not display its ema |
get_text | No usable answer tool reported an error: [ACCESS_INPUT_REQUIRED] Complete email verification in the browser form. It opens automatically when the client does not display its ema |
get_html | No usable answer tool reported an error: [ACCESS_INPUT_REQUIRED] Complete email verification in the browser form. It opens automatically when the client does not display its ema |
get_cookies | No usable answer tool reported an error: [ACCESS_INPUT_REQUIRED] Complete email verification in the browser form. It opens automatically when the client does not display its ema |
frames_list | No usable answer tool reported an error: [ACCESS_INPUT_REQUIRED] Complete email verification in the browser form. It opens automatically when the client does not display its ema |
During the calls it contacted nothing it had not already contacted.
Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.
What its tools tell an agent
In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.
1 tool with commands in capitals or very long text
- Gives the agent orders in
batch:handling as a direct call. In parallel mode, tab-scoped ops MUST pass an explicit tabId (the active-tab default is unsafe under concurrency). Use to drive several t
Common and usually harmless: it is how many makers stress how a tool should be used.
Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.
Tools
tabs_list
List open browser tabs.
screenshot selector, ref, frameId, allFrames, fullPage, format, quality, scale, tabId
Capture a screenshot (page or element). Default is JPEG (quality 70) at CSS-pixel size, which is several times smaller than PNG and reads fine. Pass format:"png" for lossless, quality 1-100 for JPEG, scale 2 for device pixels on a Retina display or 0.5 to shrink.
get_text selector, ref, frameId, allFrames, tabId, maxBytes
Get visible text of the page or an element.
get_html selector, ref, frameId, allFrames, outer, tabId, maxBytes
Get HTML of the page or an element. Output is capped (see maxBytes) and cut at a tag boundary; narrow it with `selector` rather than raising the cap when you can. Password field values are always blanked.
snapshot interactiveOnly, max, diff, failOnAuthWall, frameId, allFrames, tabId
Accessibility snapshot: interactive elements with refs to target by `ref` (more reliable than guessing CSS selectors). Pass diff:true to get only what changed since the last snapshot of this tab - far cheaper in a click/read loop. Password fields appear as secret:true with no value.
17 more tools
page_watch action, name, watchId, tabId
Save a local page checkpoint and compare it later. Actions: create (name), compare (watchId), list, delete. Stores accessibility labels and state, never form values. Site allowlist still applies.
get_cookies url, tabId
Cookies for the tab's URL (or url); values need --enable-cookie-values.
storage op, key, value, session, tabId
Read/write localStorage (or sessionStorage). op: get|set|remove|clear.
wait_for selector, textContains, gone, timeoutMs, frameId, allFrames, tabId, failOnAuthWall
Wait for a selector or text to appear/disappear.
extract_links selector, sameOriginOnly, dedupe, limit, frameId, allFrames, tabId
Extract anchors from the page or a subtree. dedupe=true collapses links sharing an href (nav/footer noise); limit caps the count.
read_as_markdown selector, frameId, allFrames, tabId, maxBytes
Read the page (or subtree) as readable markdown.
frames_list tabId
List the tab's frames (the top document plus every iframe the extension can reach), with each frame's id and URL. Use it when a selector that should match does not: the element is probably in one of these frames, and you can then pass frameId (or allFrames:true) to act inside it.
print_pdf landscape, printBackground, scale, paperWidth, paperHeight, pageRanges, preferCSSPageSize, tabId
Render the page to PDF through Chrome's own print pipeline and save it to the task's results/ dir. Returns the path and size, not the bytes - a PDF is not something to spend context on.
proxy_status
The active profile's proxy and the IP sites see. The user sets it per Chrome profile; for another IP, profile_use another profile.
chrome_status
Report backend/session status: paired browser profiles and how each was named, and flags for switched-off capabilities.
auth_check failOnAuthWall, frameId, allFrames, tabId
Is the tab sitting on a sign-in wall? Reads the page (URL, title, password fields, sign-in controls) and returns { authRequired, confidence, signals }. Use it after a navigate, or whenever a step fails unexpectedly, to tell "the session expired" apart from "the agent got lost". Pass failOnAuthWall:true to get an [AUTH_REQUIRED] error instead of a verdict, so a harness can bucket the run as an auth failure.profile_use name
Switch the active browser profile (identity). Subsequent downloads, results, screenshots, and the action log are stored under profiles/<name>/. Resets the active task to "default" unless you then call task_new.
profile_rename from, to
Rename an automatically named browser profile (e.g. "profile-2" -> "work"). The name sticks across restarts; its saved artifacts move with it.
task_new name
Start a new task (run) under the active profile. Creates profiles/<profile>/tasks/<name>/ with downloads/, results/, screenshots/ and makes it the active task so all captured artifacts land there.
tasks_list
List every task across all profiles under the data dir, with sizes and download counts.
task_status
Report the active profile/task and the folder paths where this run's artifacts are stored.
batch ops, mode, stopOnError, maxConcurrency, maxResultBytes
Run multiple tool calls in one request — parallel (default) or serial. Each op is { tool, args } and goes through the same policy gate, rate limit, and error handling as a direct call. In parallel mode, tab-scoped ops MUST pass an explicit tabId (the active-tab default is unsafe under concurrency). Use to drive several tabs at once (e.g. open tabs, then batch get_text across them). Cannot be nested.Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Files it wrote
/tmp/ .mcp-browser-extension/ access.json /tmp/ .mcp-browser-extension/ handshake.json /tmp/ .mcp-browser-extension/ hosts/ 7-default /tmp/ .mcp-browser-extension/ telemetry.json /tmp/ .mcp-browser-extension/ profiles/ default/ tasks/ default/ meta.json /tmp/ .mcp-browser-extension/ native-host/ host.sh /tmp/ .mcp-browser-extension/ native-host/ com.mehmoodqureshi.mcp_browser_extension.json /tmp/ mcp-browser-extension/ THIRD-PARTY-NOTICES.txt /tmp/ mcp-browser-extension/ icon48.png /tmp/ mcp-browser-extension/ pairing.json /tmp/ mcp-browser-extension/ icon32.png /tmp/ mcp-browser-extension/ manifest.json /tmp/ mcp-browser-extension/ activity-dashboard.css /tmp/ mcp-browser-extension/ site-protection.css /tmp/ mcp-browser-extension/ icon128.png /tmp/ mcp-browser-extension/ brand.css /tmp/ mcp-browser-extension/ options.html /tmp/ mcp-browser-extension/ popup.js /tmp/ mcp-browser-extension/ page-hook.js /tmp/ mcp-browser-extension/ icon16.png /tmp/ mcp-browser-extension/ options.js /tmp/ mcp-browser-extension/ background.js /tmp/ mcp-browser-extension/ popup.html
Paths inside its sandbox, where its home folder is /tmp and its own folder cannot be written to.
Install facts
| License | MIT |
|---|---|
| Needs | node >=20.0.0 |
| Source | github.com/Mehmoodqureshi/mcp-browser-extension |
| Install scripts | None declared by it or anything installed with it. |
| Tarball | sha512-cQza+8QNvJ62XIn0Nc5Z6OmmTNVy90hGiUqoK5MdZUORSvvGuT0oO7PnTXod/mwfrnji3PjJARd1vFld/ceoUg== |
Check this report yourself
This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.
Report as JSONExact text and tokenHow to verify it
Show it on your README
[](https://bragproof.smaverk.com/r/mcp-browser-extension)
New version out? Ask for a fresh report.