io.oxylabs/oxylabs-mcp

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Fetch and process content from specified URLs & sources using the Oxylabs Web Scraper API.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "oxylabs-mcp": {
      "url": "https://mcp.oxylabs.io/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (10)

• ai_crawler read-only

  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.

  Parameters:

  • url (required) — string — The URL from which crawling will be started.
  • user_prompt (required) — string — What information user wants to extract from the domain.
  • schema — The JSON schema to use for structured data extraction from the crawled pages. Only required if output_format is json, csv or toon.
  • geo_location — Two letter ISO country code to use for the crawl proxy.
  • output_format — string — 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 — 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 — The maximum number of sources to return.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• ai_scraper read-only

  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.

  Parameters:

  • url (required) — string — The URL to scrape
  • schema — 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 — Two letter ISO country code to use for the scrape proxy.
  • output_format — string — 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 — 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.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• ai_browser_agent read-only

  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

  Parameters:

  • url (required) — string — The URL to start the browser agent navigation from.
  • task_prompt (required) — string — What browser agent should do.
  • schema — The schema to use for the scrape. Only required if output_format is json, csv or toon.
  • geo_location — Two letter ISO country code to use for the browser proxy.
  • output_format — string — 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.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• ai_search read-only

  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.

  Parameters:

  • query (required) — string — The query to search for.
  • limit — integer — Maximum number of results to return.
  • geo_location — Two letter ISO country code to use for the search proxy.
  • return_content — boolean — Whether to return markdown content of the search results.
  • render_javascript — boolean — 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.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• generate_schema read-only

  Generate a json schema in openapi format.

  Parameters:

  • user_prompt (required) — string
  • app_name (required) — string

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• ai_map read-only

  Tool useful for mapping website's URLs.

  Parameters:

  • url (required) — string — The URL from which URLs mapping will be started.
  • limit — integer — The maximum number of URLs to return.
  • user_prompt — What kind of URLs user wants to find. Can be used together with 'search_keywords'.
  • geo_location — Two letter ISO country code to use for the mapping proxy.
  • max_crawl_depth — integer — The maximum depth of the crawl.
  • search_keywords — 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 — Whether to map subdomains URLs as well.
  • render_javascript — boolean — 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 — Whether to include external domains URLs.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• universal_scraper read-only

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

  Parameters:

  • url (required) — string — Website url to scrape.
  • render — Whether a headless browser should be used to render the page. For example: - 'html' when browser is required to render the page.
  • geo_location — 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 — 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 — Device type and browser that will be used to determine User-Agent header value.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• google_search_scraper read-only

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

  Parameters:

  • query (required) — string — URL-encoded keyword to search for.
  • limit — integer — Number of results to retrieve in each page.
  • pages — integer — Number of pages to retrieve.
  • parse — boolean — Should result be parsed. If the result is not parsed, the output_format parameter is applied.
  • domain — Domain localization for Google. Use country top level domains. For example: - 'co.uk' for United Kingdom - 'us' for United States - 'fr' for France
  • locale — 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 — 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 — If true will use the Google Ads source optimized for the paid ads.
  • start_page — integer — Starting page number.
  • geo_location — 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 — 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 — Device type and browser that will be used to determine User-Agent header value.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• amazon_search_scraper read-only

  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.

  Parameters:

  • query (required) — string — Keyword to search for.
  • pages — integer — Number of pages to retrieve.
  • parse — boolean — Should result be parsed. If the result is not parsed, the output_format parameter is applied.
  • domain — Domain localization for Google. Use country top level domains. For example: - 'co.uk' for United Kingdom - 'us' for United States - 'fr' for France
  • locale — 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 — Whether a headless browser should be used to render the page. For example: - 'html' when browser is required to render the page.
  • currency — Currency that will be used to display the prices.
  • start_page — integer — Starting page number.
  • category_id — Search for items in a particular browse node (product category).
  • merchant_id — Search for items sold by a particular seller.
  • geo_location — 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 — 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 — Device type and browser that will be used to determine User-Agent header value.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• amazon_product_scraper read-only

  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.

  Parameters:

  • query (required) — string — Keyword to search for.
  • parse — boolean — Should result be parsed. If the result is not parsed, the output_format parameter is applied.
  • domain — Domain localization for Google. Use country top level domains. For example: - 'co.uk' for United Kingdom - 'us' for United States - 'fr' for France
  • locale — 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 — Whether a headless browser should be used to render the page. For example: - 'html' when browser is required to render the page.
  • currency — Currency that will be used to display the prices.
  • geo_location — 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 — 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 — Device type and browser that will be used to determine User-Agent header value.
  • autoselect_variant — boolean — To get accurate pricing/buybox data, set this parameter to true.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.