Capguru Mcp

Launch a new Chromium browser with one page and attach the captcha solver to it. headless: run without a visible window. channel: 'chrome' or 'msedge' to use an installed browser instead of bundled Chromium. proxy: 'http://login:password@host:port' or 'login:password@host:port' (socks5:// also works).

Connect to an already running Chrome started with --remote-debugging-port and attach the solver to its first tab. Use this to solve captchas in a browser controlled by another tool.

Open a URL in the browser page. wait_until: load | domcontentloaded | networkidle.

Detect which captcha is visible on the page without solving it. Returns recaptcha2, hcaptcha, yandex, geetest, funcaptcha, tiktok, aws or 'none'.

Takes no parameters.

Solve the captcha on the current page through the Cap.Guru service. captcha_type: auto | recaptcha2 | hcaptcha | yandex (alias: other) | geetest | funcaptcha | tiktok | aws. timeout: how many seconds to wait for the captcha to appear on the page. Solving with clicks can take several minutes; progress notifications are sent every 10 s.

Get a reCAPTCHA token from Cap.Guru (method userrecaptcha) without solving images. version: v2 (with invisible=true for v2 Invisible) or v3. For v3: action (the site's action name, 'verify' if not set), min_score and enterprise=true for reCAPTCHA v3 Enterprise (sends enterprise=1). domain: google.com or recaptcha.net if the site loads reCAPTCHA from recaptcha.net. sitekey: the k / data-sitekey value. pageurl: full URL of the page. If a browser page is open, empty sitekey, pageurl, user_agent, invisible, action, enterprise and domain are taken from it; with apply_to_page=true a v2 token is put into g-recaptcha-response and the site callback is called. proxy: same format as in open_browser ('http://login:password@host:port' or 'login:password@host:port').

Get a Cloudflare Turnstile token from Cap.Guru (method turnstile). sitekey: the data-sitekey value (e.g. 0x4AAAA...). pageurl: URL of the page with Turnstile. If a browser page is open, empty sitekey/pageurl are taken from it, and with apply_to_page=true the token is put into cf-turnstile-response and the Turnstile callback is called. Usually 10-30 seconds.

Recognize a text (image) captcha through Cap.Guru (method base64) and return the text. Image source, one of: selector: the captcha image element on the open page (a screenshot of the element is sent), image_base64: image in base64 (a data: URL is also accepted), image_path: path to a local image file (png, jpg, gif, bmp, webp up to 5 MB), image_url: image URL (downloaded without cookies; use_page_cookies=true sends the page cookies). vernet: captcha kind; 0 (default) = not sent, the service chooses. Pick the kind that matches the site: 2 General v1, 6 General v2 (try 2 or 6 for distorted text), 22 Arithmetic (the service returns the expression as it is, e.g. 27+15=, and this server calculates the result), 12 Rambler, 18 General Yandex, 20 Yandex 6 characters, 16 VKontakte, 14 SolveMedia, 13 Gibdd, 9 Ok.ru, 17 World of Tanks, 5 Microsoft Hotmail. fill_selector: if set and a page is open, the answer is typed into this input.

Take a screenshot of the current page.

Return the visible text of the page (or of an element) so the page can be read without a screenshot.

Click an element by CSS selector (or Playwright selector such as text=Sign in).

Type text into an input found by selector.

Press a keyboard key (Enter, Tab, Escape, ArrowDown, Control+A ...), optionally focusing an element first.

List open tabs with their index, URL and title; the active tab is marked with *.

Takes no parameters.

Make the tab with this index (see list_tabs) the active page for all other tools.

Return the current URL and title of the page.

Takes no parameters.

Close the browser opened by open_browser (or disconnect from a connected one).

Takes no parameters.