servers / mcp-camoufox

mcp-camoufox

communitystdiolocaldestructive capablehealthy

MCP server for stealth browser automation via Camoufox — 79 tools, npx install, anti-bot stealth

Is it safe?Setup guide Alternatives Claim this server

01Tools · 133

How to read this: tool names here are observed from a live tools/list handshake. The Risk label is a heuristic inferred from the tool name (write/destructive verbs), not from executing the tool — a conservative guess, not a verified capability. We never escalate risk from a description. Found one that's wrong? Tell us — we fix on report.

Tool	Risk	Side effects	Approval
tab_list List all open tabs.	read	false	unknown
find_by_placeholder Find input by placeholder text. Returns ref + how many matched.	read	false	unknown
wait_for_navigation Wait for page load to complete.	unknown	unknown	unknown
batch_actions Execute multiple actions in one call. Each action: {type, ref?, value?, text?, key?, url?}.	unknown	unknown	unknown
get_html Get HTML content from page or element.	read	false	unknown
get_viewport_size Get current viewport dimensions.	read	false	unknown
get_links Get all links on the page with URL and text.	read	false	unknown
sessionstorage_get Get all sessionStorage data or a specific key.	read	false	unknown
sessionstorage_set Set a sessionStorage item.	write	true	unknown
back_and_snapshot Navigate back + return snapshot.	unknown	unknown	unknown
detect_anti_bot Heuristic detection of anti-bot vendor on current page (Cloudflare, DataDome, Akamai, PerimeterX, Imperva).	unknown	unknown	unknown
go_back Navigate back in history.	unknown	unknown	unknown
auth_capture Save current session as named auth state (e.g. logged-in user). Convenience wrapper: storage_state_save to ~/.camoufox-mcp/sessions/<name>.json	unknown	unknown	unknown
session_warmup Visit innocuous public sites (Google, Wikipedia) to build browsing history before targeting protected site. Helps with CF/DataDome IP scoring.	unknown	unknown	unknown
export_curl Rebuild a captured request as a runnable curl command, so you can replay or share an API call without re-deriving its headers. Needs network_start(capture_bodies=true) — headers are not recorded otherwise.	unknown	unknown	unknown
cookie_import_file Import cookies from a JSON file (Playwright format).	unknown	unknown	unknown
server_status Health check — verify server, browser status, active tabs.	read	false	unknown
get_attribute Get a specific attribute value from an element.	read	false	unknown
mouse_move Move mouse to x,y. steps>0 interpolates path (human-like).	write	true	unknown
scroll Scroll the page.	unknown	unknown	unknown
browser_launch Launch Camoufox stealth browser and navigate to URL. Browser persists between calls. By default cookies/localStorage persist in ~/.camoufox-mcp/profile. Set fresh_profile=true to start with a clean temp profile (auto-cleaned on browser_close) — useful when switching between accounts on the same domain.	unknown	unknown	unknown
get_text Get visible text from page or element.	read	false	unknown
extract_structured Extract structured data from repeated elements (cards, rows, listings). Auto-deduplicates, filters empty items, extracts direct text only. Use detect_content_pattern first to find correct selectors.	read	false	unknown
page_stats Page statistics: element count, size, load metrics. Use to decide extraction strategy.	read	false	unknown
cookie_export_file Export all cookies to a JSON file (Playwright format).	unknown	unknown	unknown
search Search the web through a search API YOU control — a self-hosted SearXNG, or Brave/Tavily/Exa with a key — and get back a normalised title/url/snippet list. This never scrapes a SERP: that shipped in 0.9.0 and was removed in 0.9.2 because engines answer some queries with confidently wrong results. A real API contract does not have that failure mode. Set MCP_SEARCH_ENDPOINT (and MCP_SEARCH_API_KEY when the provider needs one) to avoid passing them every call.	read	false	unknown
scrape_page Smart page scraper — auto-detect and extract main content, links, metadata. Strips nav/footer noise.	unknown	unknown	unknown
cookie_list List cookies.	read	false	unknown
hover Hover over element by ref ID.	unknown	unknown	unknown
wait_for_response Wait for a network response matching a URL pattern.	unknown	unknown	unknown
upload_file Upload file to file input.	write	true	unknown
tab_close Close a tab by index (-1 = active), or by url_contains.	unknown	unknown	unknown
login_classic Composite login for classic email→password forms (Google, Microsoft, generic SSO). Auto-detects the email field, clicks Next/Continue on multi-step forms, fills the password, submits, and optionally enters a TOTP 2FA code. Collapses the usual 5–8 fill/click/snapshot calls into one. Heuristic — if a form is unusual, fall back to individual fill/click tools. Returns the step log + a fresh snapshot.	read	false	unknown
drag_and_drop Drag from one element to another.	destructive	true	true
evaluate Execute JavaScript in page context.	unknown	unknown	unknown
detect_content_pattern Auto-detect repeated content patterns (cards, listings, rows) and suggest CSS selectors. Run this BEFORE extract_structured to find the right selectors.	read	false	unknown
go_forward Navigate forward in history.	unknown	unknown	unknown
reload_and_snapshot Reload page + return snapshot.	unknown	unknown	unknown
sessionstorage_clear Clear all sessionStorage for the current origin (parity with localstorage_clear).	unknown	unknown	unknown
save_pdf Save page as PDF. NOTE: Playwright can only generate PDFs in headless Chromium — Camoufox is Firefox, so this fails by design here. Use screenshot(full_page=true) instead. Kept for API compatibility.	unknown	unknown	unknown
console_get Get captured console messages.	read	false	unknown
intercept_log Show what interception blocked and allowed.	read	false	unknown
storage_snapshot Capture cookies + localStorage + sessionStorage + URL into a named slot, so storage_diff can tell you exactly what an action changed.	unknown	unknown	unknown
storage_state_save Save cookies + localStorage to a JSON file. Reload via storage_state_load on a fresh browser to skip login/CF entirely.	unknown	unknown	unknown
intercept_stop Remove interception rules and report what they blocked.	unknown	unknown	unknown
performance_timeline Navigation + paint + resource timing for the current page: TTFB, DOMContentLoaded, load, FCP, LCP, and the 5 slowest resources. Note: Firefox does not implement layout-shift, so CLS is unavailable here.	unknown	unknown	unknown
check Check checkbox or radio button.	unknown	unknown	unknown
assert_text_present Assert text is present anywhere on page (case-sensitive substring).	unknown	unknown	unknown
wait_for_url Wait for URL to match a pattern.	unknown	unknown	unknown
wait_for_change Wait until the page actually CHANGES and report what changed (url / title / DOM size / text). This is the honest version of a fixed sleep after a click: it returns as soon as something happened, or tells you nothing did.	read	false	unknown
wait_for Wait for element/text to appear or disappear.	unknown	unknown	unknown
storage_state_load Load cookies + localStorage from a JSON file (created by storage_state_save). Bypass CF/login if session is fresh.	unknown	unknown	unknown
accessibility_snapshot Get accessibility tree snapshot — compact view of page structure for LLM understanding.	read	false	unknown
list_frames List all frames/iframes in the page.	read	false	unknown
reload Reload the current page.	unknown	unknown	unknown
select_option Select option from <select> dropdown.	unknown	unknown	unknown
localstorage_clear Clear all localStorage.	unknown	unknown	unknown
mouse_replay Replay last recorded mouse path with original timing.	unknown	unknown	unknown
type_text Type text char by char via keyboard.	unknown	unknown	unknown
fingerprint_audit Report the fingerprint a site actually sees from this browser, and flag internal contradictions — the mismatches that get an automated browser detected are far more revealing than any single value. Read-only: it inspects, it does not change anything.	read	false	unknown
humanize_click Click element with humanized mouse approach (3-step Bezier-like curve before click). Use for anti-bot pages.	unknown	unknown	unknown
reset_profile Delete the persistent profile (~/.camoufox-mcp/profile) entirely. Use to start fresh — cookies, localStorage, history all wiped. Browser must be closed first (call browser_close before this).	unknown	unknown	unknown
localstorage_get Get all localStorage data or a specific key.	read	false	unknown
find_by_label Find input element by its label text (<label>). Returns ref + how many matched.	read	false	unknown
assert_clickable Hit-test an element WITHOUT clicking: would a real click actually land on it? Answers "why did my click do nothing?" before you spend the click. Reports the element that would intercept the click when something covers it.	unknown	unknown	unknown
console_start Start capturing console messages from all tabs.	unknown	unknown	unknown
query_selector_all Query elements by CSS selector, return text/attributes of all matches.	read	false	unknown
extract_table Extract data from an HTML table as JSON array.	unknown	unknown	unknown
click_at_corner Click a corner of an element — close/X buttons, delete icons and dismiss controls usually live there, not in the centre.	unknown	unknown	unknown
assert_element_visible Assert element exists and is visible. Returns success/fail (no throw).	read	false	unknown
network_get_detail Full request + response detail (headers and text body) for one captured request. Requires network_start(capture_bodies=true) BEFORE the request fired. Identify the request by id (from network_get) or by url substring.	read	false	unknown
intercept_start Block requests before they leave the browser. Blocking image/media/font/stylesheet typically removes most of a page's bytes — the single biggest speed-up for scraping — and block_urls kills trackers and ad frames. Routed on the context, so tabs opened later are covered too. Re-calling replaces the previous rules; intercept_stop removes them. 'document' cannot be blocked: it would abort the navigation itself.	unknown	unknown	unknown
smart_fill Fill form fields by their LABEL text (fuzzy, case-insensitive) instead of refs — no snapshot needed. Values go through the same clearing logic as fill, so email/number fields replace rather than append.	unknown	unknown	unknown
storage_diff Compare current storage against an earlier storage_snapshot — shows exactly which cookies/localStorage/sessionStorage keys were added, removed or changed. The fastest way to find which key holds a session token.	read	false	unknown
find_by_text Find elements by visible text — returns EVERY match (total + a ref and ancestor path per candidate), so you can tell whether the one you want is really the one you'd click. Skip browser_snapshot when you know the text.	read	false	unknown
smart_fetch Dual-mode fetch: tries the browserless HTTP path first and escalates to the stealth browser ONLY when the response looks anti-bot blocked. This is the efficiency core — high-volume reading stays cheap, the browser fires only when it's actually needed.	read	false	unknown
http_session_cookies Show which browser cookies would be sent with an HTTP request to this URL. Use it to confirm session sharing before relying on http_request.	read	false	unknown
click Click element by ref ID from browser_snapshot. Auto JS-fallback for overlays.	unknown	unknown	unknown
screenshot Screenshot the page, or a single element with ref/selector (great for documenting one modal). Returns the IMAGE inline — no second Read call — plus the saved path. Set return_image=false for path only.	read	false	unknown
paste_text Fill a field with a REAL paste. Puts the text on the clipboard and presses Ctrl/Cmd+V so the page receives a trusted paste event with actual clipboardData — the only thing that works for frameworks that listen to paste alone (Svelte 5 / SolidJS runes, some Qwik forms). Falls back to a synthetic event and then the native value setter.	unknown	unknown	unknown
search_page Grep the CURRENT page's visible text and return matches with surrounding context. Costs nothing compared to a snapshot or a screenshot — use it first to find where a term actually appears.	read	false	unknown
mouse_click_xy Click at exact x,y coordinates. steps>0 adds interpolated pre-movement (human-like).	unknown	unknown	unknown
frame_evaluate Execute JavaScript inside a specific frame/iframe.	unknown	unknown	unknown
inject_init_script Inject a script that runs before every page load.	unknown	unknown	unknown
indexeddb_list List IndexedDB databases for the current origin. Many SPAs keep auth state and drafts here, invisible to cookie/localStorage tools.	read	false	unknown
export_har Export captured network traffic as a HAR 1.2 file (openable in DevTools/other HAR viewers). Requires network_start first; headers and bodies are only included when network_start(capture_bodies=true) was used.	unknown	unknown	unknown
tab_select Switch to a tab by index, or by url_contains (first tab whose URL contains the substring).	unknown	unknown	unknown
describe_page Compact LLM-friendly page summary (title, heading, key buttons, forms). Cheaper than browser_snapshot for agent context. Also returns `intent` — a classified hint of what kind of page this is (login_email, login_password, otp_input, captcha, stay_signed_in, protect_account, error_page, consent, two_factor, account_disabled, content, unknown) — so the agent can branch with one read.	read	false	unknown
click_element_offset Click at a percentage position inside an element instead of its centre — for wide labels whose real checkbox sits at the left edge, sliders, or split buttons.	unknown	unknown	unknown
fill Fill input/textarea by ref ID. Always replaces existing content (email/number inputs are cleared explicitly first — Firefox's select-all is a no-op on those, which would otherwise append).	unknown	unknown	unknown
workflow_run Run a list of tool calls in sequence — any tool this server exposes, by name — and return a per-step log. Resumable: a failed run tells you the index, and start_at skips the steps that already succeeded. Each step is {"tool":"navigate","args":{"url":"…"},"label":"optional"}.	write	true	unknown
click_and_wait Click element then wait for navigation or selector. Atomic — fewer roundtrips than separate click + wait_for.	unknown	unknown	unknown
network_get List captured network requests in capture order, keeping the most recent `limit` rows. Each row shows an #id usable with network_get_detail.	read	false	unknown
assert_url_matches Assert current URL matches pattern (substring or regex).	unknown	unknown	unknown
wait_for_network_idle Wait until there are no in-flight requests for idle_ms continuously. Requests are counted from the moment the page was opened, so one that was ALREADY in flight when you call this is not mistaken for idle.	unknown	unknown	unknown
dialog_auto_handle Install a PERSISTENT dialog handler that stays armed across every dialog and every tab (dialog_handle is one-shot). Reads its action at fire time, so you can change it without re-arming. Set enabled=false to remove it.	unknown	unknown	unknown
dialog_handle Set handler for the next alert/confirm/prompt on ANY open tab (first dialog wins, handler then clears).	unknown	unknown	unknown
click_and_snapshot Click element by ref + wait + return snapshot. Perfect for buttons that trigger navigation/dialog.	unknown	unknown	unknown
click_text Click element by visible text. If the text matches several elements it FAILS with a numbered candidate list instead of silently clicking the first one — narrow with within ("@dialog", a CSS selector, or "ref:e5") or pick one with index.	read	false	unknown
cookie_import Import cookies from JSON (from cookie_export). Restores session state.	unknown	unknown	unknown
navigate_and_snapshot Navigate to URL then return snapshot — combined in one call.	unknown	unknown	unknown
humanize_type Type text with Gaussian-distributed delays between keystrokes (mean ~80ms, sigma ~30ms). Mimics human typing rhythm.	unknown	unknown	unknown
tab_new Open new tab.	unknown	unknown	unknown
navigate Navigate to a URL.	unknown	unknown	unknown
cookie_delete Delete cookies. Both empty = clear all.	destructive	true	true
inspect_element Get detailed info about an element (tag, attributes, bounding box, styles).	read	false	unknown
cookie_set Set a cookie. IMPORTANT: with expires_days=0 this creates a SESSION cookie, which Firefox keeps in memory only — it is gone after browser_close even though the profile itself persists. Pass expires_days (e.g. 30) to write a login session that survives a relaunch.	write	true	unknown
browser_close Close the browser. Cookies are preserved in the persistent profile (~/.camoufox-mcp/profile). If the launch used fresh_profile=true, the temp profile is removed.	unknown	unknown	unknown
press_key Press key or combo (Enter, Escape, Control+a, etc.).	unknown	unknown	unknown
get_page_errors Get uncaught JavaScript errors + unhandled promise rejections from the current page. Captured by a hook installed at browser_launch, so the buffer resets on every navigation (read it before navigating away). Max 100 entries per page load.	read	false	unknown
click_role Click element by ARIA role and name. Same ambiguity guard as click_text: several matches → candidate list, not a guess.	read	false	unknown
click_turnstile Auto-solve Cloudflare Interactive Turnstile checkbox. Locates the widget via in-page selectors AND the Playwright frame API (handles closed shadow roots that document.querySelector misses), polls for render, skips if already solved, then does a humanized real-mouse click with retries + small nudge, verifying the cf-turnstile-response token after each attempt. Managed Challenge full-page interstitials still need mcp-stealth-chrome.	unknown	unknown	unknown
mouse_drift Random mouse movements over a duration — builds up mouse history before action (CF/DataDome behavior analysis).	unknown	unknown	unknown
wait_and_snapshot Wait for selector/text then return snapshot. Combines wait_for + browser_snapshot in one call.	unknown	unknown	unknown
indexeddb_delete Delete an IndexedDB database by name for the current origin (clears SPA state that survives a cookie wipe).	destructive	true	true
scroll_to Scroll a specific element into view (the page-level `scroll` tool only moves by pixels).	read	false	unknown
form_introspect Analyse a form in one call: per field the label, type, current value, required/pattern/length constraints, validation state, and the JS framework it is bound to. Tells you what to fill and why a submit is being rejected without guessing from a snapshot.	unknown	unknown	unknown
wait_for_request Block until the page ISSUES a request matching a URL substring (wait_for_response waits for the reply). Use it to confirm an action actually fired its API call.	unknown	unknown	unknown
uncheck Uncheck a checkbox.	unknown	unknown	unknown
get_url Get current URL and title.	read	false	unknown
scrape_markdown Fetch a URL and return clean, LLM-ready markdown (headings, links, lists preserved; nav/footer/scripts stripped). Default path is browserless (impit) — fast and cheap. Set use_browser=true for JS-rendered pages (needs browser_launch).	read	false	unknown
cookie_export Export all cookies as JSON string. Use with cookie_import to transfer session.	unknown	unknown	unknown
browser_recover Escape hatch when the browser is wedged and browser_close can't complete: force-drops the connection and resets server state so browser_launch works again. Also reports a profile lock held by another Camoufox process, which is the usual cause of 'A copy of Camoufox is already open'.	unknown	unknown	unknown
browser_snapshot Get visible interactive elements with ref IDs. Use refs with click/fill. Always call after navigation. On large pages (Outlook, dashboards) the response can be truncated — narrow with roles=["button","textbox"] or paginate with offset/limit. Refs stay stable regardless of filters (every visible element is still numbered).	read	false	unknown
wait_for_any_of Race multiple wait conditions — returns the first that matches, so the agent can branch immediately without sequential probes. Each condition is {kind: 'selector'\|'text'\|'url_contains'\|'title_contains', value: string}. Returns the index + kind + value of the winning condition (or 'timeout' if none matched). Ideal for post-login flows where the next page could be any of several (e.g. 'Stay signed in?', 'Skip for now', or the inbox directly).	read	false	unknown
mouse_record Start recording mouse positions in the page (replay with mouse_replay). Re-calling replaces any previous recorder instead of leaking its listener.	unknown	unknown	unknown
chatgpt_generate_image Generate or edit an image on chatgpt.com end-to-end and save it to disk in ONE call. Opens a fresh chat, optionally uploads reference images (e.g. a brand logo), submits the prompt, waits for the generated image to finish, then writes the result PNG to output_path. Requires an authenticated chatgpt.com session (import cookies first via cookie_import). Returns the saved path and pixel dimensions. Note: chatgpt image generation is slow (~60-120s) — set timeout_ms accordingly.	read	false	unknown
chatgpt_generate_batch Generate MANY images on chatgpt.com IN PARALLEL (one tab per job, fire-all-then-collect) and save each to disk. Submits every job first WITHOUT waiting, then waits for all generations concurrently — far faster than sequential. For a CONSISTENT feed set, pass shared_image_paths (e.g. [logo] and/or a style-reference image like a previously-generated hero) uploaded to EVERY tab, plus style_suffix (a shared style spec) appended to every prompt. Requires an authenticated chatgpt.com session (import cookies first). Returns per-job results (saved path / ok / bytes / error).	read	false	unknown
network_start Start capturing network requests. With capture_bodies=true also records request/response headers + text bodies (json/text/xml/form only, capped at body_limit bytes) so you can inspect API payloads via network_get_detail — no need to pivot to evaluate()+fetch().	read	false	unknown
fill_form Fill multiple form fields and optionally submit.	unknown	unknown	unknown
localstorage_set Set a localStorage item.	write	true	unknown
set_viewport_size Set the viewport width and height. This is the exact control over what the page renders and what a screenshot captures. It does NOT resize the OS window: Camoufox reports a frozen outerWidth/outerHeight, so asking for a viewport larger than the launch window makes the content bigger than its own window — impossible geometry that a detector can read. The reply says so when that happens.	write	true	unknown
http_request HTTP request WITHOUT a browser, using a real Firefox TLS/HTTP2 fingerprint (impit). By default it reuses the live browser's cookies for that URL, so you can log in with the browser and then hit the site's API cheaply. Far faster and lighter than navigating — use it for APIs, JSON, and any page that doesn't need JS.	unknown	unknown	unknown

02Install & source

npx -y mcp-camoufox@latest

npx

repohttps://github.com/RobithYusuf/mcp-camoufox
licenseMIT
adoption19 stars · 5 forks

03Access granted

Workflow automation · write

The access this server can exercise, inferred from its verified tools — not a declared OAuth scope.

05Provenance & freshness

sourcesGitHub repo search [p4]

last_checked2026-09-20 15:23Z

next_check2026-09-20 18:23Z

cadenceevery 3h

verifiedmetadata:passed metadata:passed metadata:passed metadata:passed metadata:passed metadata:passed metadata:passed metadata:passed metadata:passed metadata:passed

index_statusindex — 9 unique facts >= 5

06Badge

Add the “as seen on MCPExplorer” badge to your README.

[![mcp-camoufox MCP — as seen on mcpexplorer.com](https://mcpexplorer.com/badge/mcp-camoufox.svg)](https://mcpexplorer.com/servers/mcp-camoufox)

Next step

This is one server. A loadout combines the right servers, governance, and proven plays for a whole job — assembled deliberately, not tool-dumped.

Explore loadouts →