dev.oassis/scraper-crawler

Est-ce que dev.oassis/scraper-crawler est sûr ?

Au dernier audit MCP Hub, le serveur MCP « dev.oassis/scraper-crawler » 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 14 outils

• web_act≈ 2042 tokens

  Runs actions against an open session and returns the resulting state. Actions: {navigate}, {click:{ref}}, {type:{ref,text,clear}}, {select:{ref,value}}, {press}, {scroll}, {wait}, {back}. The `ref` is the one `controls` gave you. It stops at the first failure and tells you where. $0.0005 (0.25 credit) per action, plus requested outputs and any outstanding browser time. API key and credits required. Reference for the oassis API: https://oassis.dev/openapi.json

  Paramètres, retour & exemple (16)

  Paramètres

  • pdf · object · optionnel
    Options for the `pdf` format: `format` (a4, letter, legal…), `landscape`, `printBackground`, `scale` 0.1 to 2.
  • url · string · optionnel
    Page to process.
  • json · object · optionnel
    For the `json` format: a `prompt` describing what to pull out, a JSON `schema` to fill, or both.
  • wait · object · optionnel
    When to consider the page loaded: `until` (load, domcontentloaded, networkidle0, networkidle2), `selector` to wait for, `timeout` in ms.
  • block · object · optionnel
    What not to load, which makes a render faster and cheaper. `resourceTypes` takes image, font, stylesheet, media… and `urlPatterns` are regular expressions, not globs: `\.svg$`, not `*.svg`.
  • links · object · optionnel
    Options for the `links` format: `visibleOnly`, `excludeExternal` to keep only internal links.
  • maxAge · integer · optionnel
    Accept an answer up to this many milliseconds old. A cache hit costs $0.0002 instead of the format price. Leave it out to force a fresh render.
  • actions · array · requis
    What to do, in order: click, type, select, scroll, hover, press, navigate, wait. One to twenty-five per call.
  • formats · array · optionnel
    Outputs you want in the same response. `controls` is the map of what can be clicked; `elements` needs `selectors`; `json` needs `json.prompt` or `json.schema`.
  • request · object · optionnel
    How to make the request: `headers`, `cookies`, `userAgent`, and `auth` for basic authentication.
  • binaryAs · string · optionnel · base64
    How a screenshot or a PDF comes back. `base64` is the only value today.
  • controls · object · optionnel
    Options for the `controls` format: `visibleOnly`, and `limit` (1 to 1000) to cut the map.
  • viewport · object · optionnel
    The window to render in: `width`, `height`, `deviceScaleFactor`.
  • selectors · array · optionnel
    CSS selectors for the `elements` format.
  • sessionId · string · requis
    The session to act on, from `web_session_open`.
  • screenshot · object · optionnel
    Options for the `screenshot` format: `fullPage` for the whole page, `type` (png, jpeg, webp), `quality` 1-100 (not with png), `omitBackground`, `selector` to capture one element, and its own `viewport`.

  Exemple d'appel

  {"name": "web_act", "arguments": {"actions": [], "sessionId": "texte"}}

  Exemple de retour

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

• web_batch_status≈ 184 tokens

  Checks a batch of scrapes: status, how many are done, and the results. Free for the owning account. Pass `cancel: true` to stop it.

  Paramètres, retour & exemple (3)

  Paramètres

  • jobId · string · requis
    The batch, from web_scrape_batch.
  • limit · number · optionnel
    Results to return (default 50).
  • cancel · boolean · optionnel
    Stop pending pages and refund pages that never started. An in-flight read may finish and is billed; failed reads are refunded.

  Exemple d'appel

  {"name": "web_batch_status", "arguments": {"jobId": "texte"}}

  Exemple de retour

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

• web_crawl≈ 1349 tokens

  Follows a site's links and reads every page. Returns a jobId; poll it with web_crawl_status. API key and credits required; `limit` controls the maximum pages charged. Use web_map first if you only need the urls. Reference for the oassis API: https://oassis.dev/openapi.json

  Paramètres, retour & exemple (17)

  Paramètres

  • url · string · requis
    Page to process.
  • json · object · optionnel
    For the `json` format: a `prompt` describing what to pull out, a JSON `schema` to fill, or both.
  • wait · object · optionnel
    When to consider the page loaded: `until` (load, domcontentloaded, networkidle0, networkidle2), `selector` to wait for, `timeout` in ms.
  • block · object · optionnel
    What not to load, which makes a render faster and cheaper. `resourceTypes` takes image, font, stylesheet, media… and `urlPatterns` are regular expressions, not globs: `\.svg$`, not `*.svg`.
  • limit · integer · optionnel
    Pages this crawl may read, up to 200. Charged up front; what it does not read comes back.
  • links · object · optionnel
    Options for the `links` format: `visibleOnly`, `excludeExternal` to keep only internal links.
  • maxAge · integer · optionnel
    Accept an answer up to this many milliseconds old. A cache hit costs $0.0002 instead of the format price. Leave it out to force a fresh render.
  • formats · array · optionnel
    Outputs you want in the same response. `controls` is the map of what can be clicked; `elements` needs `selectors`; `json` needs `json.prompt` or `json.schema`. A screenshot or a PDF is not available here: every result is kept until you collect it. Ask for those one url at a time on web_scrape.
  • request · object · optionnel
    How to make the request: `headers`, `cookies`, `userAgent`, and `auth` for basic authentication.
  • binaryAs · string · optionnel · base64
    How a screenshot or a PDF comes back. `base64` is the only value today.
  • controls · object · optionnel
    Options for the `controls` format: `visibleOnly`, and `limit` (1 to 1000) to cut the map.
  • maxDepth · integer · optionnel
    How far from the starting page to follow links. 0 reads only the starting page.
  • viewport · object · optionnel
    The window to render in: `width`, `height`, `deviceScaleFactor`.
  • selectors · array · optionnel
    CSS selectors for the `elements` format.
  • excludePaths · array · optionnel
    Discard urls whose path contains one of these. Up to twenty. It wins over `includePaths`.
  • includePaths · array · optionnel
    Keep only urls whose path contains one of these. Up to twenty.
  • includeSubdomains · boolean · optionnel
    Treat subdomains of the same site as part of it.

  Exemple d'appel

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

  Exemple de retour

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

• web_crawl_status≈ 187 tokens

  Checks a crawl: status, pages read, discovered and still queued, and the pages themselves. Free for the owning account. Pass `cancel: true` to stop it.

  Paramètres, retour & exemple (3)

  Paramètres

  • jobId · string · requis
    The crawl, from web_crawl.
  • limit · number · optionnel
    Pages to return (default 50).
  • cancel · boolean · optionnel
    Stop pending pages and refund pages that never started. An in-flight read may finish and is billed; failed reads are refunded.

  Exemple d'appel

  {"name": "web_crawl_status", "arguments": {"jobId": "texte"}}

  Exemple de retour

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

• web_feedback≈ 326 tokens

  Tell us an answer was good or bad. FREE. Use it when a result is wrong — empty markdown, a control map missing a button, data that does not match the page — with the url or the jobId so it can be reproduced. It is the only way we learn that we read a page badly: our logs cannot tell that apart from a page that is simply like that. Reference for the oassis API: https://oassis.dev/openapi.json

  Paramètres, retour & exemple (5)

  Paramètres

  • url · string · optionnel
    The page that came out wrong: usually the fastest way to reproduce it.
  • route · string · optionnel
    Which tool or endpoint it is about, as you called it.
  • comment · string · optionnel
    What you expected and what you got.
  • verdict · string · requis · good | bad
    Did the answer do the job or not.
  • reference · string · optionnel
    The jobId or sessionId it happened on, so it can be looked up.

  Exemple d'appel

  {"name": "web_feedback", "arguments": {"verdict": "good"}}

  Exemple de retour

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

• web_map≈ 396 tokens

  Every url of a site, fast and cheap: its sitemap plus, optionally, the links on the page. Use it BEFORE crawling, to see what is there and decide what is worth reading. 1 credit ($0.002) with `includePage: false` (no browser at all), 1.5 credits ($0.003) with the page. Reference for the oassis API: https://oassis.dev/openapi.json

  Paramètres, retour & exemple (7)

  Paramètres

  • url · string · requis
    Page to process.
  • limit · integer · optionnel
    Urls to return. Up to 5000.
  • search · string · optionnel
    Keep only urls containing this text.
  • includePage · boolean · optionnel
    Render the page too, to catch urls the sitemap does not list. `false` uses no browser at all, so it costs less: $0.002 against $0.003.
  • excludePaths · array · optionnel
    Discard urls whose path contains one of these. Up to twenty. It wins over `includePaths`.
  • includePaths · array · optionnel
    Keep only urls whose path contains one of these. Up to twenty.
  • includeSubdomains · boolean · optionnel
    Treat subdomains of the same site as part of it.

  Exemple d'appel

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

  Exemple de retour

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

• web_scrape≈ 1534 tokens

  Processes a page and returns every output you ask for at once: markdown, html, links, screenshot, PDF, accessibility tree, elements by selector, AI-structured data, and `controls` (what can be clicked). One call, and a partial failure does not void the rest. From 1 credit ($0.002) per output. A url pointing at a PDF, Word, Excel or CSV file is converted to markdown instead, with no browser, for $0.002. Reference for the oassis API: https://oassis.dev/openapi.json

  Paramètres, retour & exemple (15)

  Paramètres

  • pdf · object · optionnel
    Options for the `pdf` format: `format` (a4, letter, legal…), `landscape`, `printBackground`, `scale` 0.1 to 2.
  • url · string · optionnel
    Page to process.
  • html · string · optionnel
    Raw HTML instead of `url`, for a page you already have. Nothing leaves for the network.
  • json · object · optionnel
    For the `json` format: a `prompt` describing what to pull out, a JSON `schema` to fill, or both.
  • wait · object · optionnel
    When to consider the page loaded: `until` (load, domcontentloaded, networkidle0, networkidle2), `selector` to wait for, `timeout` in ms.
  • block · object · optionnel
    What not to load, which makes a render faster and cheaper. `resourceTypes` takes image, font, stylesheet, media… and `urlPatterns` are regular expressions, not globs: `\.svg$`, not `*.svg`.
  • links · object · optionnel
    Options for the `links` format: `visibleOnly`, `excludeExternal` to keep only internal links.
  • maxAge · integer · optionnel
    Accept an answer up to this many milliseconds old. A cache hit costs $0.0002 instead of the format price. Leave it out to force a fresh render.
  • formats · array · optionnel
    Outputs you want in the same response. `controls` is the map of what can be clicked; `elements` needs `selectors`; `json` needs `json.prompt` or `json.schema`.
  • request · object · optionnel
    How to make the request: `headers`, `cookies`, `userAgent`, and `auth` for basic authentication.
  • binaryAs · string · optionnel · base64
    How a screenshot or a PDF comes back. `base64` is the only value today.
  • controls · object · optionnel
    Options for the `controls` format: `visibleOnly`, and `limit` (1 to 1000) to cut the map.
  • viewport · object · optionnel
    The window to render in: `width`, `height`, `deviceScaleFactor`.
  • selectors · array · optionnel
    CSS selectors for the `elements` format.
  • screenshot · object · optionnel
    Options for the `screenshot` format: `fullPage` for the whole page, `type` (png, jpeg, webp), `quality` 1-100 (not with png), `omitBackground`, `selector` to capture one element, and its own `viewport`.

  Exemple d'appel

  {"name": "web_scrape", "arguments": {"pdf": {}, "url": "texte", "html": "texte", "json": {}, "wait": {}, "block": {}}}

  Exemple de retour

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

• web_scrape_batch≈ 1158 tokens

  A batch OF SCRAPES: reads a list of urls YOU give it (2 to 50, from any sites) and returns a jobId. It discovers nothing on its own — for that use web_crawl. API key and credits required. Poll it with web_batch_status.

  Paramètres, retour & exemple (12)

  Paramètres

  • json · object · optionnel
    For the `json` format: a `prompt` describing what to pull out, a JSON `schema` to fill, or both.
  • urls · array · requis
    The pages of this batch. Two to fifty, no duplicates: a batch charges per url.
  • wait · object · optionnel
    When to consider the page loaded: `until` (load, domcontentloaded, networkidle0, networkidle2), `selector` to wait for, `timeout` in ms.
  • block · object · optionnel
    What not to load, which makes a render faster and cheaper. `resourceTypes` takes image, font, stylesheet, media… and `urlPatterns` are regular expressions, not globs: `\.svg$`, not `*.svg`.
  • links · object · optionnel
    Options for the `links` format: `visibleOnly`, `excludeExternal` to keep only internal links.
  • maxAge · integer · optionnel
    Accept an answer up to this many milliseconds old. A cache hit costs $0.0002 instead of the format price. Leave it out to force a fresh render.
  • formats · array · optionnel
    Outputs you want in the same response. `controls` is the map of what can be clicked; `elements` needs `selectors`; `json` needs `json.prompt` or `json.schema`. A screenshot or a PDF is not available here: every result is kept until you collect it. Ask for those one url at a time on web_scrape.
  • request · object · optionnel
    How to make the request: `headers`, `cookies`, `userAgent`, and `auth` for basic authentication.
  • binaryAs · string · optionnel · base64
    How a screenshot or a PDF comes back. `base64` is the only value today.
  • controls · object · optionnel
    Options for the `controls` format: `visibleOnly`, and `limit` (1 to 1000) to cut the map.
  • viewport · object · optionnel
    The window to render in: `width`, `height`, `deviceScaleFactor`.
  • selectors · array · optionnel
    CSS selectors for the `elements` format.

  Exemple d'appel

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

  Exemple de retour

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

• web_search_exa≈ 382 tokens

  Search the web with Exa's index: a query instead of a url, for when you do not know where to look. Returns title, url and a snippet per result. To read the pages, pass the urls to web_scrape_batch. The engine is named because the price is Exa's, passed through with no markup and read from its own payment challenge on every call — the quote is read at execution time and is not a guaranteed fixed price. API key and credits required over MCP.

  Paramètres, retour & exemple (6)

  Paramètres

  • limit · integer · optionnel
    Results to return. Up to 50.
  • query · string · requis
    What to search for.
  • since · string · optionnel
    Only results published after this ISO date.
  • domains · array · optionnel
    Only these domains, subdomains included: `example.com` also matches `docs.example.com`.
  • snippets · boolean · optionnel
    Text alongside each result. On by default: a bare url is rarely enough.
  • excludeDomains · array · optionnel
    Never these domains, subdomains included.

  Exemple d'appel

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

  Exemple de retour

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

• web_session_close≈ 152 tokens

  Closes the browser session and stops its time. HTTP equivalent: POST /web/v1/session/{id}/close. No additional close fee; outstanding browser time is settled when applicable. If you do not close it, it closes itself after a minute without use.

  Paramètres, retour & exemple (1)

  Paramètres

  • sessionId · string · requis
    The session to close, from web_session_open.

  Exemple d'appel

  {"name": "web_session_close", "arguments": {"sessionId": "texte"}}

  Exemple de retour

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

• web_session_open≈ 1469 tokens

  Opens a browser session and returns the map of controls. Opening costs 2.5 credits plus the requested outputs; the first minute is included. Further started minutes cost 2 credits with an account key. Use web_act to interact and web_session_close when done. API key and credits required. Reference: https://oassis.dev/openapi.json

  Paramètres, retour & exemple (14)

  Paramètres

  • pdf · object · optionnel
    Options for the `pdf` format: `format` (a4, letter, legal…), `landscape`, `printBackground`, `scale` 0.1 to 2.
  • url · string · requis
    Page to process.
  • json · object · optionnel
    For the `json` format: a `prompt` describing what to pull out, a JSON `schema` to fill, or both.
  • wait · object · optionnel
    When to consider the page loaded: `until` (load, domcontentloaded, networkidle0, networkidle2), `selector` to wait for, `timeout` in ms.
  • block · object · optionnel
    What not to load, which makes a render faster and cheaper. `resourceTypes` takes image, font, stylesheet, media… and `urlPatterns` are regular expressions, not globs: `\.svg$`, not `*.svg`.
  • links · object · optionnel
    Options for the `links` format: `visibleOnly`, `excludeExternal` to keep only internal links.
  • maxAge · integer · optionnel
    Accept an answer up to this many milliseconds old. A cache hit costs $0.0002 instead of the format price. Leave it out to force a fresh render.
  • formats · array · optionnel
    Outputs you want in the same response. `controls` is the map of what can be clicked; `elements` needs `selectors`; `json` needs `json.prompt` or `json.schema`.
  • request · object · optionnel
    How to make the request: `headers`, `cookies`, `userAgent`, and `auth` for basic authentication.
  • binaryAs · string · optionnel · base64
    How a screenshot or a PDF comes back. `base64` is the only value today.
  • controls · object · optionnel
    Options for the `controls` format: `visibleOnly`, and `limit` (1 to 1000) to cut the map.
  • viewport · object · optionnel
    The window to render in: `width`, `height`, `deviceScaleFactor`.
  • selectors · array · optionnel
    CSS selectors for the `elements` format.
  • screenshot · object · optionnel
    Options for the `screenshot` format: `fullPage` for the whole page, `type` (png, jpeg, webp), `quality` 1-100 (not with png), `omitBackground`, `selector` to capture one element, and its own `viewport`.

  Exemple d'appel

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

  Exemple de retour

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

• web_task_cancel≈ 168 tokens

  Stops a task using its owning API key, or its legacy access_token. No new operations start. Cancellation is free; unused account credit reservations are released. Cancelling a finished task changes nothing.

  Paramètres, retour & exemple (2)

  Paramètres

  • id · string · requis
    The task id, from web_task_start.
  • access_token · string · optionnel
    Task-scoped access token returned by web_task_start; not an API key.

  Exemple d'appel

  {"name": "web_task_cancel", "arguments": {"id": "texte"}}

  Exemple de retour

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

• web_task_start≈ 440 tokens

  Starts a research task: a question answered by reading public pages, with sources, progress and cost. Requires an API key and credits. The maximum budget is reserved, actual execution cost is charged, and unused credits are released. Returns a task id: check it with web_task_status.

  Paramètres, retour & exemple (4)

  Paramètres

  • mode · string · optionnel · research
    Only research is available: read public pages and answer.
  • task · string · requis
    What to find out, in plain words. Be specific about what to compare.
  • urls · array · optionnel
    Pages to read first, up to 5. Public http or https urls only.
  • limits · object · optionnel
    Bounds on cost, time and steps.

  Exemple d'appel

  {"name": "web_task_start", "arguments": {"task": "texte"}}

  Exemple de retour

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

• web_task_status≈ 140 tokens

  Returns a task's status, progress, sources, limitations, result and billing. Only your own tasks.

  Paramètres, retour & exemple (2)

  Paramètres

  • id · string · requis
    The task id, from web_task_start.
  • access_token · string · optionnel
    Task-scoped access token returned by web_task_start; not an API key.

  Exemple d'appel

  {"name": "web_task_status", "arguments": {"id": "texte"}}

  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.oassis.dev/mcp