com.hydrafetch/web

Est-ce que com.hydrafetch/web est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.hydrafetch/web » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 13 outils

• batch≈ 244 tokens

  Scrape a list of URLs you already have, such as pages found with map. Waits for the batch to finish and returns the first page of results in the same call, so a short list needs one call; read further pages, or a batch still running, with batch_status. Each URL scraped costs 1 credit.

  Paramètres, retour & exemple (3)

  Paramètres

  • urls · array · requis
    The URLs to scrape.
  • wait · integer · optionnel
    Seconds to wait for the batch before returning (default 45). 0 returns the batch id at once.
  • limit · integer · optionnel
    Results to return in this call (default 10).

  Exemple d'appel

  {"name": "batch", "arguments": {"urls": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• batch_status≈ 232 tokens

  Read a batch started with batch: its progress, and one page of results in the order the URLs were sent. When nextOffset is not null, pass it as offset to read the next page of results.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Results to return in this call (default 10).
  • offset · integer · optionnel
    Position of the first result to return. Defaults to 0.
  • batchId · string · requis
    The id returned by batch.

  Exemple d'appel

  {"name": "batch_status", "arguments": {"batchId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• brand≈ 141 tokens

  A company's brand from its domain: logos for light and dark backgrounds, its colours, name, description and social profiles. Use it to answer what a company is or how it presents itself.

  Paramètres, retour & exemple (1)

  Paramètres

  • domain · string · requis
    The company domain, e.g. stripe.com. A full URL works too.

  Exemple d'appel

  {"name": "brand", "arguments": {"domain": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• crawl≈ 204 tokens

  Discover and scrape the pages of a website as one background job, following its links from a starting URL. Returns a crawl id straight away; read progress and results with crawl_status. Each page scraped costs 1 credit, so set limit to what you need.

  Paramètres, retour & exemple (3)

  Paramètres

  • url · string · requis
    The site to start from.
  • limit · integer · optionnel
    Maximum pages to scrape.
  • maxDepth · integer · optionnel
    How far from the seed to follow.

  Exemple d'appel

  {"name": "crawl", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• crawl_status≈ 226 tokens

  Read a crawl started with crawl: its progress, and one page of the scraped results. When nextOffset is not null, pass it as offset to read the next page of results.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Results to return in this call (default 10).
  • offset · integer · optionnel
    Position of the first result to return. Defaults to 0.
  • crawlId · string · requis
    The id returned by crawl.

  Exemple d'appel

  {"name": "crawl_status", "arguments": {"crawlId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• extract≈ 304 tokens

  Pull specific fields out of one or more pages as JSON, shaped by a JSON schema or described in a prompt. Use it when you need values such as prices, names or dates rather than the whole page text.

  Paramètres, retour & exemple (6)

  Paramètres

  • urls · array · requis
    The URLs to extract from.
  • prompt · string · optionnel
    Natural-language description of what to pull.
  • schema · object · optionnel
    A JSON schema the result must conform to.
  • showSources · boolean · optionnel
    Return the list of URLs that were actually extracted.
  • showConfidence · boolean · optionnel
    For each field, return a confidence score and the exact source passage the value was drawn from.
  • preferStructure · boolean · optionnel
    Keep headings, lists and tables in the text handed to the model.

  Exemple d'appel

  {"name": "extract", "arguments": {"urls": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• images≈ 126 tokens

  Harvest a page's images with their metadata, without rendering it. Cheaper than a screenshot and returns the source images rather than a picture of the page.

  Paramètres, retour & exemple (1)

  Paramètres

  • url · string · requis
    The page to harvest images from.

  Exemple d'appel

  {"name": "images", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• logo≈ 217 tokens

  A company's logo as a directly embeddable image URL, chosen for the background you name. Use this rather than brand when the mark is all you need: it costs a fifth as much and returns one asset instead of the whole record.

  Paramètres, retour & exemple (3)

  Paramètres

  • type · string · optionnel · icon | wordmark
    The square mark, or the full logotype. Defaults to icon.
  • theme · string · optionnel · light | dark | auto
    The background the logo will sit on. Defaults to light.
  • domain · string · requis
    The company domain, e.g. stripe.com. A full URL works too.

  Exemple d'appel

  {"name": "logo", "arguments": {"domain": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• map≈ 148 tokens

  List the URLs on a website, found through its sitemap and links, without fetching their content. Use it to see which pages exist before choosing which to scrape.

  Paramètres, retour & exemple (2)

  Paramètres

  • url · string · requis
    The seed URL to map.
  • limit · integer · optionnel
    Max URLs to return.

  Exemple d'appel

  {"name": "map", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• scrape≈ 264 tokens

  Fetch one web page and return its main content as clean markdown, with optional HTML, links or structured data. Use it to read a page whose URL you already have. For many pages of one site use crawl; for a list of URLs use batch.

  Paramètres, retour & exemple (3)

  Paramètres

  • url · string · requis
    The URL to scrape.
  • formats · array · optionnel
    Which outputs to return. Defaults to markdown.
  • preferStructure · boolean · optionnel
    Keep headings, lists and tables as markdown. Default false optimises for raw content and can return unstructured text on marketing and listing pages. Turn on when the document structure matters, or retry with it if `structure` came back 'plain'.

  Exemple d'appel

  {"name": "scrape", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• screenshot≈ 432 tokens

  Render a page in a real browser and capture a PNG, returning its public URL. Use when the question is what the page looks like rather than what it says.

  Paramètres, retour & exemple (8)

  Paramètres

  • url · string · requis
    The URL to capture.
  • maxAge · integer · optionnel
    Reuse a stored screenshot younger than this many milliseconds. Defaults to 7 days, so a repeat returns the stored PNG without re-rendering and without applying waitFor. Pass 0 to force a fresh capture.
  • timeout · integer · optionnel
    Overall time budget for the capture, in milliseconds.
  • waitFor · integer · optionnel
    Extra milliseconds to let the page settle before capture.
  • fullPage · boolean · optionnel
    Capture the whole scrollable page rather than the viewport.
  • viewport · string · optionnel · desktop | laptop | tablet | mobile
    Screen size to render at. Defaults to desktop (1920x1080). Ignored when width or height are given.
  • viewportWidth · integer · optionnel
    Exact viewport width in pixels. Overrides viewport.
  • viewportHeight · integer · optionnel
    Exact viewport height in pixels. Overrides viewport. With fullPage the capture still extends to the full page height.

  Exemple d'appel

  {"name": "screenshot", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search≈ 209 tokens

  Search the web and return ranked results: title, url and snippet. Set scrapeResults to also fetch each result as markdown, at 1 extra credit per page.

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · integer · optionnel
    Max results (default 5).
  • query · string · requis
    The search query.
  • scrapeResults · boolean · optionnel
    Also scrape each result to markdown, 1 extra credit per page (default false).
  • preferStructure · boolean · optionnel
    Keep headings, lists and tables in each scraped result.

  Exemple d'appel

  {"name": "search", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• styleguide≈ 290 tokens

  A site's design tokens read from computed styles in a real browser: colours by role with contrast ratios, the dark theme colours when the site has one, the type scale, corner radius and button styling, how panels, the header bar and panel titles are drawn, plus ready-made CSS, Tailwind and shadcn/ui stylesheets. Values defined through CSS variables come back resolved to the hex actually painted. To recreate how a site looks rather than only its tokens, take a screenshot of the page too.

  Paramètres, retour & exemple (3)

  Paramètres

  • url · string · optionnel
    One page to read instead of the homepage, e.g. https://stripe.com/pricing.
  • domain · string · optionnel
    The domain to read, e.g. stripe.com, using its homepage. Send this or url.
  • maxAge · integer · optionnel
    Accept a stored result no older than this many milliseconds. 0 reads fresh.

  Exemple d'appel

  {"name": "styleguide", "arguments": {"url": "texte", "domain": "texte", "maxAge": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://api.hydrafetch.com/mcp