io.oxylabs/oxylabs-mcp

Est-ce que io.oxylabs/oxylabs-mcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.oxylabs/oxylabs-mcp » 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 10 outils

• ai_browser_agent≈ 414 tokens

  Run the browser agent and return the data in the specified format. This tool is useful if you need navigate around the website and do some actions. It allows navigating to any url, clicking on links, filling forms, scrolling, etc. Finally it returns the data in the specified format. Schema is required only if output_format is json, csv or toon. 'task_prompt' describes what browser agent should achieve

  Paramètres, retour & exemple (5)

  Paramètres

  • url · string · requis
    The URL to start the browser agent navigation from.
  • schema · ? · optionnel
    The schema to use for the scrape. Only required if output_format is json, csv or toon.
  • task_prompt · string · requis
    What browser agent should do.
  • geo_location · ? · optionnel
    Two letter ISO country code to use for the browser proxy.
  • output_format · string · optionnel · json | markdown | html | csv | toon
    The output format. Markdown returns full text of the page including links. Toon(Token-Oriented Object Notation) returns data in Toon format, which is optimized for AI agents. If json, csv or toon, the schema is required.

  Exemple d'appel

  {"name": "ai_browser_agent", "arguments": {"url": "texte", "task_prompt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• ai_crawler≈ 542 tokens

  Tool useful for crawling a website from starting url and returning data in a specified format. Schema is required only if output_format is json, csv or toon. 'render_javascript' is used to render javascript heavy websites. 'return_sources_limit' is used to limit the number of sources to return, for example if you expect results from single source, you can set it to 1.

  Paramètres, retour & exemple (7)

  Paramètres

  • url · string · requis
    The URL from which crawling will be started.
  • schema · ? · optionnel
    The JSON schema to use for structured data extraction from the crawled pages. Only required if output_format is json, csv or toon.
  • user_prompt · string · requis
    What information user wants to extract from the domain.
  • geo_location · ? · optionnel
    Two letter ISO country code to use for the crawl proxy.
  • output_format · string · optionnel · json | markdown | csv | toon
    The format of the output. If json, csv or toon, the schema is required. Markdown returns full text of the page. CSV returns data in CSV format. Toon(Token-Oriented Object Notation) returns data in Toon format, which is optimized for AI agents.
  • render_javascript · boolean · optionnel
    Whether to render the HTML of the page using javascript. Much slower, therefore use it only for websites that require javascript to render the page. Unless user asks to use it, first try to crawl the page without it. If results are unsatisfactory, try to use it.
  • return_sources_limit · integer · optionnel
    The maximum number of sources to return.

  Exemple d'appel

  {"name": "ai_crawler", "arguments": {"url": "texte", "user_prompt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• ai_map≈ 470 tokens

  Tool useful for mapping website's URLs.

  Paramètres, retour & exemple (9)

  Paramètres

  • url · string · requis
    The URL from which URLs mapping will be started.
  • limit · integer · optionnel
    The maximum number of URLs to return.
  • user_prompt · ? · optionnel
    What kind of URLs user wants to find. Can be used together with 'search_keywords'.
  • geo_location · ? · optionnel
    Two letter ISO country code to use for the mapping proxy.
  • max_crawl_depth · integer · optionnel
    The maximum depth of the crawl.
  • search_keywords · ? · optionnel
    The keywords to use for URLs paths filtering. Keywords are matched as OR condition. Meaning, one keyword is enough to match the url path.
  • allow_subdomains · boolean · optionnel
    Whether to map subdomains URLs as well.
  • render_javascript · boolean · optionnel
    Whether to render the HTML of the page using javascript. Much slower, therefore use it only for websites that require javascript to render the page. Unless user asks to use it, first try to crawl the page without it. If results are unsatisfactory, try to use it.
  • allow_external_domains · boolean · optionnel
    Whether to include external domains URLs.

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• ai_scraper≈ 433 tokens

  Scrape the contents of the web page and return the data in the specified format. Schema is required only if output_format is json or csv. 'render_javascript' is used to render javascript heavy websites.

  Paramètres, retour & exemple (5)

  Paramètres

  • url · string · requis
    The URL to scrape
  • schema · ? · optionnel
    The JSON schema to use for structured data extraction from the scraped page. Only required if output_format is json, csv or toon.
  • geo_location · ? · optionnel
    Two letter ISO country code to use for the scrape proxy.
  • output_format · string · optionnel · json | markdown | csv | toon
    The format of the output. If json, csv or toon, the schema is required. Markdown returns full text of the page. CSV returns data in CSV format, tabular like data. Toon(Token-Oriented Object Notation) returns data in Toon format, which is optimized for AI agents.
  • render_javascript · boolean · optionnel
    Whether to render the HTML of the page using javascript. Much slower, therefore use it only for websites that require javascript to render the page.Unless user asks to use it, first try to scrape the page without it. If results are unsatisfactory, try to use it.

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• ai_search≈ 356 tokens

  Search the web based on a provided query. 'return_content' is used to return markdown content for each search result. If 'return_content' is set to True, you don't need to use ai_scraper to get the content of the search results urls, because it is already included in the search results. if 'return_content' is set to True, prefer lower 'limit' to reduce payload size.

  Paramètres, retour & exemple (5)

  Paramètres

  • limit · integer · optionnel
    Maximum number of results to return.
  • query · string · requis
    The query to search for.
  • geo_location · ? · optionnel
    Two letter ISO country code to use for the search proxy.
  • return_content · boolean · optionnel
    Whether to return markdown content of the search results.
  • render_javascript · boolean · optionnel
    Whether to render the HTML of the page using javascript. Much slower, therefore use it only if user asks to use it.First try to search with setting it to False.

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• amazon_product_scraper≈ 926 tokens

  Scrape Amazon products. Supports content parsing, different user agent types, domain, geolocation, locale parameters and different output formats. Supports Amazon specific parameters such as currency and getting more accurate pricing data with auto select variant.

  Paramètres, retour & exemple (10)

  Paramètres

  • parse · boolean · optionnel
    Should result be parsed. If the result is not parsed, the output_format parameter is applied.
  • query · string · requis
    Keyword to search for.
  • domain · ? · optionnel
    Domain localization for Google. Use country top level domains. For example: - 'co.uk' for United Kingdom - 'us' for United States - 'fr' for France
  • locale · ? · optionnel
    Set 'Accept-Language' header value which changes your Google search page web interface language. Examples: - 'en-US' for English, United States - 'de-AT' for German, Austria - 'fr-FR' for French, France
  • render · ? · optionnel
    Whether a headless browser should be used to render the page. For example: - 'html' when browser is required to render the page.
  • currency · ? · optionnel
    Currency that will be used to display the prices.
  • geo_location · ? · optionnel
    The geographical location that the result should be adapted for. Use ISO-3166 country codes. Examples: - 'California, United States' - 'Mexico' - 'US' for United States - 'DE' for Germany - 'FR' for France
  • output_format · ? · optionnel
    The format of the output. Works only when parse parameter is false. - links - Most efficient when the goal is navigation or finding specific URLs. Use this first when you need to locate a specific page within a website. - md - Best for extracting and reading visible content once you've found the right page. Use this to get structured content that's easy to read and process. - html - Should be used sparingly only when you need the raw HTML structure, JavaScript code, or styling information.
  • user_agent_type · ? · optionnel
    Device type and browser that will be used to determine User-Agent header value.
  • autoselect_variant · boolean · optionnel
    To get accurate pricing/buybox data, set this parameter to true.

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• amazon_search_scraper≈ 1008 tokens

  Scrape Amazon search results. Supports content parsing, different user agent types, pagination, domain, geolocation, locale parameters and different output formats. Supports Amazon specific parameters such as category id, merchant id, currency.

  Paramètres, retour & exemple (13)

  Paramètres

  • pages · integer · optionnel
    Number of pages to retrieve.
  • parse · boolean · optionnel
    Should result be parsed. If the result is not parsed, the output_format parameter is applied.
  • query · string · requis
    Keyword to search for.
  • domain · ? · optionnel
    Domain localization for Google. Use country top level domains. For example: - 'co.uk' for United Kingdom - 'us' for United States - 'fr' for France
  • locale · ? · optionnel
    Set 'Accept-Language' header value which changes your Google search page web interface language. Examples: - 'en-US' for English, United States - 'de-AT' for German, Austria - 'fr-FR' for French, France
  • render · ? · optionnel
    Whether a headless browser should be used to render the page. For example: - 'html' when browser is required to render the page.
  • currency · ? · optionnel
    Currency that will be used to display the prices.
  • start_page · integer · optionnel
    Starting page number.
  • category_id · ? · optionnel
    Search for items in a particular browse node (product category).
  • merchant_id · ? · optionnel
    Search for items sold by a particular seller.
  • geo_location · ? · optionnel
    The geographical location that the result should be adapted for. Use ISO-3166 country codes. Examples: - 'California, United States' - 'Mexico' - 'US' for United States - 'DE' for Germany - 'FR' for France
  • output_format · ? · optionnel
    The format of the output. Works only when parse parameter is false. - links - Most efficient when the goal is navigation or finding specific URLs. Use this first when you need to locate a specific page within a website. - md - Best for extracting and reading visible content once you've found the right page. Use this to get structured content that's easy to read and process. - html - Should be used sparingly only when you need the raw HTML structure, JavaScript code, or styling information.
  • user_agent_type · ? · optionnel
    Device type and browser that will be used to determine User-Agent header value.

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• generate_schema≈ 127 tokens

  Generate a json schema in openapi format.

  Paramètres, retour & exemple (2)

  Paramètres

  • app_name · string · requis · ai_crawler | ai_scraper | browser_agent
  • user_prompt · string · requis

  Exemple d'appel

  {"name": "generate_schema", "arguments": {"app_name": "ai_crawler", "user_prompt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• google_search_scraper≈ 927 tokens

  Scrape Google Search results. Supports content parsing, different user agent types, pagination, domain, geolocation, locale parameters and different output formats.

  Paramètres, retour & exemple (12)

  Paramètres

  • limit · integer · optionnel
    Number of results to retrieve in each page.
  • pages · integer · optionnel
    Number of pages to retrieve.
  • parse · boolean · optionnel
    Should result be parsed. If the result is not parsed, the output_format parameter is applied.
  • query · string · requis
    URL-encoded keyword to search for.
  • domain · ? · optionnel
    Domain localization for Google. Use country top level domains. For example: - 'co.uk' for United Kingdom - 'us' for United States - 'fr' for France
  • locale · ? · optionnel
    Set 'Accept-Language' header value which changes your Google search page web interface language. Examples: - 'en-US' for English, United States - 'de-AT' for German, Austria - 'fr-FR' for French, France
  • render · ? · optionnel
    Whether a headless browser should be used to render the page. For example: - 'html' when browser is required to render the page.
  • ad_mode · boolean · optionnel
    If true will use the Google Ads source optimized for the paid ads.
  • start_page · integer · optionnel
    Starting page number.
  • geo_location · ? · optionnel
    The geographical location that the result should be adapted for. Use ISO-3166 country codes. Examples: - 'California, United States' - 'Mexico' - 'US' for United States - 'DE' for Germany - 'FR' for France
  • output_format · ? · optionnel
    The format of the output. Works only when parse parameter is false. - links - Most efficient when the goal is navigation or finding specific URLs. Use this first when you need to locate a specific page within a website. - md - Best for extracting and reading visible content once you've found the right page. Use this to get structured content that's easy to read and process. - html - Should be used sparingly only when you need the raw HTML structure, JavaScript code, or styling information.
  • user_agent_type · ? · optionnel
    Device type and browser that will be used to determine User-Agent header value.

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• universal_scraper≈ 575 tokens

  Get a content of any webpage. Supports browser rendering, parsing of certain webpages and different output formats.

  Paramètres, retour & exemple (5)

  Paramètres

  • url · string · requis
    Website url to scrape.
  • render · ? · optionnel
    Whether a headless browser should be used to render the page. For example: - 'html' when browser is required to render the page.
  • geo_location · ? · optionnel
    The geographical location that the result should be adapted for. Use ISO-3166 country codes. Examples: - 'California, United States' - 'Mexico' - 'US' for United States - 'DE' for Germany - 'FR' for France
  • output_format · ? · optionnel
    The format of the output. Works only when parse parameter is false. - links - Most efficient when the goal is navigation or finding specific URLs. Use this first when you need to locate a specific page within a website. - md - Best for extracting and reading visible content once you've found the right page. Use this to get structured content that's easy to read and process. - html - Should be used sparingly only when you need the raw HTML structure, JavaScript code, or styling information.
  • user_agent_type · ? · optionnel
    Device type and browser that will be used to determine User-Agent header value.

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

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://mcp.oxylabs.io/mcp