@mozilla/firefox-devtools-mcp
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: nothing
What it contacted
Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.
Starting it
npx -y @mozilla/firefox-devtools-mcp@0.10.7
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.
list_pages | No usable answer tool reported an error: Error: Process (pid=100) unexpectedly closed with status 255 |
get_page_text | No usable answer tool reported an error: Error: Process (pid=108) unexpectedly closed with status 255 |
list_downloads | No usable answer tool reported an error: Error: Process (pid=116) unexpectedly closed with status 255 |
get_firefox_output | No usable answer tool reported an error: Error: Process (pid=124) unexpectedly closed with status 255 |
get_firefox_info | No usable answer tool reported an error: Error: Process (pid=132) unexpectedly closed with status 255 |
During the calls (not necessarily because of them) it first contacted: ftp.mozilla.org, github.com, plausible.io, product-details.mozilla.org, raw.githubusercontent.com, release-assets.githubusercontent.com (a release file downloaded from GitHub).
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.
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
list_pages
List open tabs (index, title, URL). Selected tab is marked.
new_page url, wait
Open new tab at URL. Returns tab index.
navigate_page url, wait
Navigate selected tab to URL.
select_page pageIdx, url, title
Select active tab by index, URL, or title. Index takes precedence.
close_page pageIdx
Close tab by index.
30 more tools
get_page_text maxLength, saveTo, preview
Get the visible text of the page (document.body.innerText). Caps at maxLength (default 20000 chars); saveTo saves the full text to a file.
take_snapshot maxLines, includeAttributes, includeText, maxDepth, includeAll, selector, saveTo, preview
Capture DOM snapshot with stable UIDs. A UID stays valid across snapshots until its element is removed or the page navigates. Output caps at maxLines (default 100); scope with selector or dump the full tree with saveTo.
resolve_uid_to_selector uid
Resolve UID to CSS selector. Fails if the element is gone.
clear_snapshot
Clear snapshot UIDs. Usually not needed.
click_by_uid uid, dblClick
Click element by UID. Set dblClick for double-click.
hover_by_uid uid
Hover over element by UID.
fill_by_uid uid, value
Fill text input/textarea by UID.
drag_by_uid_to_uid fromUid, toUid
Drag element to another (HTML5 drag events).
fill_form_by_uid elements
Fill multiple form fields at once.
upload_file_by_uid uid, filePath
Upload file to file input by UID.
press_key key, uid
Press a single key, optionally with modifiers, to submit, dismiss, navigate or trigger a shortcut. Not for entering text: use fill_by_uid instead.
type_text text, uid, submitKey
Type text key by key into the focused element, optionally followed by a key such as Enter. Use fill_by_uid to set the value of a known input; use this for elements that only react to real typing, such as autocomplete fields and rich text editors.
screenshot_page fullPage, saveTo
Capture viewport screenshot as base64 PNG. Set fullPage for the whole scrollable document.
screenshot_by_uid uid, saveTo
Capture element screenshot by UID as base64 PNG.
print_page landscape, background, saveTo
Print the current page to a PDF file using print CSS. Returns the saved file path.
list_downloads status, urlContains, limit, format
List downloads tracked since startup, including status and saved file path.
clear_downloads
Clear the tracked downloads buffer.
set_download_behavior behavior, downloadFolder
Control how downloads are handled: allow (save to a destination folder), deny (cancel), or reset to default. Avoids the native save-file dialog. Requires a recent Firefox.
accept_dialog promptText
Accept browser dialog. Provide promptText for prompts.
dismiss_dialog
Dismiss browser dialog.
navigate_history direction
Navigate history back/forward. UIDs become stale.
set_viewport_size width, height
Set viewport dimensions in pixels. Applies to the selected tab only.
get_firefox_output lines, grep, since
Retrieve Firefox output (stdout/stderr including MOZ_LOG, warnings, crashes, stack traces). Returns recent output from the capture file. Use filters to focus on specific content.
get_firefox_info
Get information about the current Firefox instance configuration, including binary path, environment variables, and output file location.
close_firefox_session
Ends the browser session. If the server connected to your existing Firefox, this releases the connection and leaves Firefox running. If the server started Firefox itself, this closes it. Call this when the browser task is complete and no further browser interaction is expected.
install_extension type, path, value, permanent
Install a Firefox extension using WebDriver BiDi webExtension.install command. Supports installing from archive (.xpi/.zip), base64-encoded data, or unpacked directory.
uninstall_extension id
Uninstall a Firefox extension using WebDriver BiDi webExtension.uninstall command. Requires the extension ID returned by install_extension or obtained from list_extensions.
screencast_start context, frameRate, width, height, mimeType
Start recording a screencast (video) of the current page viewport, saving the output to a file in the downloads directory. Returns a screencast id to pass to screencast_stop. Multiple recordings can run at once.
screencast_stop screencast
Stop an in-progress screencast recording started with screencast_start and finalize the video file. Returns the path to the saved file.
evaluate_script function, args, timeout, sandbox, saveTo, preview
Run a JS function in the page and return its result. Prefer this for targeted reads (a value, text, computed style, whether an element exists) instead of a full take_snapshot. Use the UID interaction tools for clicking, typing, and filling.
Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Files it wrote
/tmp/ .cache/ selenium/ se-metadata.json
Paths inside its sandbox, where its home folder is /tmp and its own folder cannot be written to.
Install facts
| License | MIT OR Apache-2.0 |
|---|---|
| Needs | node >=20.19.0 |
| Source | github.com/mozilla/firefox-devtools-mcp |
| Install scripts | geckodriver declare them. This runner does not run them. |
| Tarball | sha512-TJWTPR6ZKfe39JndcB/nvJC52PmpmsMvpu5Gt4iauQDOXZDXjqBJi1vVABJncxMo7HQwfoN0rWPJHAK1g3Ue/A== |
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/%40mozilla/firefox-devtools-mcp)
New version out? Ask for a fresh report.