Firefox MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Browse and debug the web with Firefox. Use this for any browser or web page task: opening a URL, automating a web flow, or debugging a page (console errors, network requests, DOM state). The task does not need to name Firefox, reach for these tools unless another browser is explicitly requested. Chrome-only browser tools do not control Firefox, do not assume they cover this.
Enabled capabilities:
pages: Open, navigate, select, and close pages.
snapshot: Capture accessibility/DOM snapshots and resolve UIDs.
input: Interact with the page via UID-based clicks, typing, key presses, drag, and uploads.
screenshot: Capture screenshots of the page or specific elements.
print: Print the page to PDF.
downloads: Monitor and manage file downloads.
utilities: Handle dialogs, history navigation, and viewport sizing.
management: Inspect Firefox options and logs, and close the browser.
webextension: Install and uninstall web extensions.
screencast: Record screencasts of the page viewport (Firefox 154+).
script: Evaluate arbitrary JavaScript in the page context.
When these tools are deferred, load the core set in one search rather than one at a time: list_pages, new_page, navigate_page, take_snapshot, get_page_text. Add task-specific tools to the same search: click_by_uid / fill_by_uid / hover_by_uid for interaction, screenshot_page / screenshot_by_uid for visuals, evaluate_script for one-off JS.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_pagesA | List open tabs (index, title, URL). Selected tab is marked. |
| new_pageB | Open new tab at URL. Returns tab index. |
| navigate_pageB | Navigate selected tab to URL. |
| select_pageA | Select active tab by index, URL, or title. Index takes precedence. |
| close_pageA | Close tab by index. |
| get_page_textA | 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_snapshotA | 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_selectorA | Resolve UID to CSS selector. Fails if the element is gone. |
| clear_snapshotC | Clear snapshot UIDs. Usually not needed. |
| click_by_uidA | Click element by UID. Set dblClick for double-click. |
| hover_by_uidB | Hover over element by UID. |
| fill_by_uidB | Fill text input/textarea by UID. |
| drag_by_uid_to_uidB | Drag element to another (HTML5 drag events). |
| fill_form_by_uidA | Fill multiple form fields at once. |
| upload_file_by_uidB | Upload file to file input by UID. |
| press_keyA | 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_textA | 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_pageB | Capture viewport screenshot as base64 PNG. Set fullPage for the whole scrollable document. |
| screenshot_by_uidA | Capture element screenshot by UID as base64 PNG. |
| print_pageB | Print the current page to a PDF file using print CSS. Returns the saved file path. |
| list_downloadsA | List downloads tracked since startup, including status and saved file path. |
| clear_downloadsA | Clear the tracked downloads buffer. |
| set_download_behaviorA | 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_dialogA | Accept browser dialog. Provide promptText for prompts. |
| dismiss_dialogA | Dismiss browser dialog. |
| navigate_historyA | Navigate history back/forward. UIDs become stale. |
| set_viewport_sizeA | Set viewport dimensions in pixels. Applies to the selected tab only. |
| get_firefox_outputA | 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_infoA | Get information about the current Firefox instance configuration, including binary path, environment variables, and output file location. |
| close_firefox_sessionA | 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_extensionA | Install a Firefox extension using WebDriver BiDi webExtension.install command. Supports installing from archive (.xpi/.zip), base64-encoded data, or unpacked directory. |
| uninstall_extensionA | Uninstall a Firefox extension using WebDriver BiDi webExtension.uninstall command. Requires the extension ID returned by install_extension or obtained from list_extensions. |
| screencast_startA | 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_stopA | Stop an in-progress screencast recording started with screencast_start and finalize the video file. Returns the path to the saved file. |
| evaluate_scriptA | 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. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 35 tools
Most tools target distinct resource+action pairs (navigation, DOM interaction, screenshots, downloads, dialogs, viewport, extensions, screencasts). There is mild overlap between fill_by_uid/type_text/fill_form_by_uid and between get_page_text/take_snapshot/evaluate_script, but descriptions explicitly steer the agent toward the right one in each case.
Names are overwhelmingly consistent snake_case verb_noun (list_pages, navigate_page, close_page, take_snapshot, click_by_uid, set_viewport_size). Minor deviations like new_page (instead of create_page) and the take_/get_ verb mix for content retrieval are readable and do not break the pattern.
35 tools is on the heavy side for a single server, though the breadth of a full browser-automation surface (tabs, DOM, forms, screenshots, downloads, dialogs, extensions, screencasts) justifies most of them. It is borderline: the surface could be trimmed or grouped without losing capability, so a heavy-but-defensible score.
Covers the browser lifecycle very thoroughly: page CRUD, navigation, DOM interaction, forms, uploads, downloads, dialogs, viewport, extension management, screencasts, JS eval, and process info/output. Minor gaps remain—uninstall_extension references a list_extensions tool that isn't present, and there is no explicit wait-for-condition or cookie/storage management.