oxylabs-mcp

{'type': 'object', 'required': ['url', 'task_prompt'], 'properties': {'url': {'type': 'string', 'description': 'The URL to start the browser agent navigation from.'}, 'schema': {'anyOf': [{'type': 'object', 'additionalProperties': True}, {'type': 'null'}], 'default': None, 'description': 'The schema to use for the scrape. Only required if output_format is json, csv or toon.'}, 'task_prompt': {'type': 'string', 'description': 'What browser agent should do.'}, 'geo_location': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Two letter ISO country code to use for the browser proxy.'}, 'output_format': {'enum': ['json', 'markdown', 'html', 'csv', 'toon'], 'type': 'string', 'default': 'markdown', 'description': '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.'}}, 'additionalProperties': False}

{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}

{'type': 'object', 'required': ['url', 'user_prompt'], 'properties': {'url': {'type': 'string', 'description': 'The URL from which crawling will be started.'}, 'schema': {'anyOf': [{'type': 'object', 'additionalProperties': True}, {'type': 'null'}], 'default': None, 'description': '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': {'type': 'string', 'description': 'What information user wants to extract from the domain.'}, 'geo_location': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Two letter ISO country code to use for the crawl proxy.'}, 'output_format': {'enum': ['json', 'markdown', 'csv', 'toon'], 'type': 'string', 'default': 'markdown', 'description': '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': {'type': 'boolean', 'default': False, 'description': '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': {'type': 'integer', 'default': 25, 'maximum': 50, 'description': 'The maximum number of sources to return.'}}, 'additionalProperties': False}

{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}

{'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'The URL from which URLs mapping will be started.'}, 'limit': {'type': 'integer', 'default': 25, 'maximum': 50, 'description': 'The maximum number of URLs to return.'}, 'user_prompt': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': "What kind of URLs user wants to find. Can be used together with 'search_keywords'."}, 'geo_location': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Two letter ISO country code to use for the mapping proxy.'}, 'max_crawl_depth': {'type': 'integer', 'default': 1, 'maximum': 5, 'description': 'The maximum depth of the crawl.'}, 'search_keywords': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'default': None, 'description': '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': {'type': 'boolean', 'default': False, 'description': 'Whether to map subdomains URLs as well.'}, 'render_javascript': {'type': 'boolean', 'default': False, 'description': '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': {'type': 'boolean', 'default': False, 'description': 'Whether to include external domains URLs.'}}, 'additionalProperties': False}

{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}

{'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'The URL to scrape'}, 'schema': {'anyOf': [{'type': 'object', 'additionalProperties': True}, {'type': 'null'}], 'default': None, 'description': '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': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Two letter ISO country code to use for the scrape proxy.'}, 'output_format': {'enum': ['json', 'markdown', 'csv', 'toon'], 'type': 'string', 'default': 'markdown', 'description': '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': {'type': 'boolean', 'default': False, 'description': '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.'}}, 'additionalProperties': False}

{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}

{'type': 'object', 'required': ['query'], 'properties': {'limit': {'type': 'integer', 'default': 10, 'maximum': 50, 'description': 'Maximum number of results to return.'}, 'query': {'type': 'string', 'description': 'The query to search for.'}, 'geo_location': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Two letter ISO country code to use for the search proxy.'}, 'return_content': {'type': 'boolean', 'default': False, 'description': 'Whether to return markdown content of the search results.'}, 'render_javascript': {'type': 'boolean', 'default': False, 'description': '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. '}}, 'additionalProperties': False}

{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}

{'type': 'object', 'required': ['query'], 'properties': {'parse': {'type': 'boolean', 'default': True, 'description': 'Should result be parsed. If the result is not parsed, the output_format parameter is applied.'}, 'query': {'type': 'string', 'description': 'Keyword to search for.'}, 'domain': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'examples': ['uk', 'us', 'fr'], 'description': "\n        Domain localization for Google.\n        Use country top level domains.\n        For example:\n            - 'co.uk' for United Kingdom\n            - 'us' for United States\n            - 'fr' for France\n        "}, 'locale': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'examples': ['en-US', 'de-AT', 'fr-FR'], 'description': "\n        Set 'Accept-Language' header value which changes your Google search page web interface language.\n        Examples:\n            - 'en-US' for English, United States\n            - 'de-AT' for German, Austria\n            - 'fr-FR' for French, France\n        "}, 'render': {'anyOf': [{'type': 'string', 'const': 'html'}, {'type': 'null'}], 'default': None, 'examples': ['html'], 'description': "\n        Whether a headless browser should be used to render the page.\n        For example:\n            - 'html' when browser is required to render the page.\n        "}, 'currency': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'examples': ['USD', 'EUR', 'AUD'], 'description': 'Currency that will be used to display the prices.'}, 'geo_location': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'examples': ['US', 'DE', 'FR'], 'description': "\n        The geographical location that the result should be adapted for.\n        Use ISO-3166 country codes.\n        Examples:\n            - 'California, United States'\n            - 'Mexico'\n            - 'US' for United States\n            - 'DE' for Germany\n            - 'FR' for France\n        "}, 'output_format': {'anyOf': [{'enum': ['links', 'md', 'html'], 'type': 'string'}, {'type': 'null'}], 'default': None, 'description': "\n        The format of the output. Works only when parse parameter is false.\n            - 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.\n            - 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.\n            - html - Should be used sparingly only when you need the raw HTML structure, JavaScript code, or styling information.\n        "}, 'user_agent_type': {'anyOf': [{'enum': ['desktop', 'desktop_chrome', 'desktop_firefox', 'desktop_safari', 'desktop_edge', 'desktop_opera', 'mobile', 'mobile_ios', 'mobile_android', 'tablet'], 'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Device type and browser that will be used to determine User-Agent header value.'}, 'autoselect_variant': {'type': 'boolean', 'default': False, 'description': 'To get accurate pricing/buybox data, set this parameter to true.'}}, 'additionalProperties': False}

{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}

{'type': 'object', 'required': ['query'], 'properties': {'pages': {'type': 'integer', 'default': 0, 'description': 'Number of pages to retrieve.'}, 'parse': {'type': 'boolean', 'default': True, 'description': 'Should result be parsed. If the result is not parsed, the output_format parameter is applied.'}, 'query': {'type': 'string', 'description': 'Keyword to search for.'}, 'domain': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'examples': ['uk', 'us', 'fr'], 'description': "\n        Domain localization for Google.\n        Use country top level domains.\n        For example:\n            - 'co.uk' for United Kingdom\n            - 'us' for United States\n            - 'fr' for France\n        "}, 'locale': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'examples': ['en-US', 'de-AT', 'fr-FR'], 'description': "\n        Set 'Accept-Language' header value which changes your Google search page web interface language.\n        Examples:\n            - 'en-US' for English, United States\n            - 'de-AT' for German, Austria\n            - 'fr-FR' for French, France\n        "}, 'render': {'anyOf': [{'type': 'string', 'const': 'html'}, {'type': 'null'}], 'default': None, 'examples': ['html'], 'description': "\n        Whether a headless browser should be used to render the page.\n        For example:\n            - 'html' when browser is required to render the page.\n        "}, 'currency': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'examples': ['USD', 'EUR', 'AUD'], 'description': 'Currency that will be used to display the prices.'}, 'start_page': {'type': 'integer', 'default': 0, 'description': 'Starting page number.'}, 'category_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Search for items in a particular browse node (product category).'}, 'merchant_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Search for items sold by a particular seller.'}, 'geo_location': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'examples': ['US', 'DE', 'FR'], 'description': "\n        The geographical location that the result should be adapted for.\n        Use ISO-3166 country codes.\n        Examples:\n            - 'California, United States'\n            - 'Mexico'\n            - 'US' for United States\n            - 'DE' for Germany\n            - 'FR' for France\n        "}, 'output_format': {'anyOf': [{'enum': ['links', 'md', 'html'], 'type': 'string'}, {'type': 'null'}], 'default': None, 'description': "\n        The format of the output. Works only when parse parameter is false.\n            - 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.\n            - 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.\n            - html - Should be used sparingly only when you need the raw HTML structure, JavaScript code, or styling information.\n        "}, 'user_agent_type': {'anyOf': [{'enum': ['desktop', 'desktop_chrome', 'desktop_firefox', 'desktop_safari', 'desktop_edge', 'desktop_opera', 'mobile', 'mobile_ios', 'mobile_android', 'tablet'], 'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Device type and browser that will be used to determine User-Agent header value.'}}, 'additionalProperties': False}

{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}

{'type': 'object', 'required': ['user_prompt', 'app_name'], 'properties': {'app_name': {'enum': ['ai_crawler', 'ai_scraper', 'browser_agent'], 'type': 'string'}, 'user_prompt': {'type': 'string'}}, 'additionalProperties': False}

{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}

{'type': 'object', 'required': ['query'], 'properties': {'limit': {'type': 'integer', 'default': 0, 'description': 'Number of results to retrieve in each page.'}, 'pages': {'type': 'integer', 'default': 0, 'description': 'Number of pages to retrieve.'}, 'parse': {'type': 'boolean', 'default': True, 'description': 'Should result be parsed. If the result is not parsed, the output_format parameter is applied.'}, 'query': {'type': 'string', 'description': 'URL-encoded keyword to search for.'}, 'domain': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'examples': ['uk', 'us', 'fr'], 'description': "\n        Domain localization for Google.\n        Use country top level domains.\n        For example:\n            - 'co.uk' for United Kingdom\n            - 'us' for United States\n            - 'fr' for France\n        "}, 'locale': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'examples': ['en-US', 'de-AT', 'fr-FR'], 'description': "\n        Set 'Accept-Language' header value which changes your Google search page web interface language.\n        Examples:\n            - 'en-US' for English, United States\n            - 'de-AT' for German, Austria\n            - 'fr-FR' for French, France\n        "}, 'render': {'anyOf': [{'type': 'string', 'const': 'html'}, {'type': 'null'}], 'default': None, 'examples': ['html'], 'description': "\n        Whether a headless browser should be used to render the page.\n        For example:\n            - 'html' when browser is required to render the page.\n        "}, 'ad_mode': {'type': 'boolean', 'default': False, 'description': 'If true will use the Google Ads source optimized for the paid ads.'}, 'start_page': {'type': 'integer', 'default': 0, 'description': 'Starting page number.'}, 'geo_location': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'examples': ['US', 'DE', 'FR'], 'description': "\n        The geographical location that the result should be adapted for.\n        Use ISO-3166 country codes.\n        Examples:\n            - 'California, United States'\n            - 'Mexico'\n            - 'US' for United States\n            - 'DE' for Germany\n            - 'FR' for France\n        "}, 'output_format': {'anyOf': [{'enum': ['links', 'md', 'html'], 'type': 'string'}, {'type': 'null'}], 'default': None, 'description': "\n        The format of the output. Works only when parse parameter is false.\n            - 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.\n            - 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.\n            - html - Should be used sparingly only when you need the raw HTML structure, JavaScript code, or styling information.\n        "}, 'user_agent_type': {'anyOf': [{'enum': ['desktop', 'desktop_chrome', 'desktop_firefox', 'desktop_safari', 'desktop_edge', 'desktop_opera', 'mobile', 'mobile_ios', 'mobile_android', 'tablet'], 'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Device type and browser that will be used to determine User-Agent header value.'}}, 'additionalProperties': False}

{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}

{'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'Website url to scrape.'}, 'render': {'anyOf': [{'type': 'string', 'const': 'html'}, {'type': 'null'}], 'default': None, 'examples': ['html'], 'description': "\n        Whether a headless browser should be used to render the page.\n        For example:\n            - 'html' when browser is required to render the page.\n        "}, 'geo_location': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'examples': ['US', 'DE', 'FR'], 'description': "\n        The geographical location that the result should be adapted for.\n        Use ISO-3166 country codes.\n        Examples:\n            - 'California, United States'\n            - 'Mexico'\n            - 'US' for United States\n            - 'DE' for Germany\n            - 'FR' for France\n        "}, 'output_format': {'anyOf': [{'enum': ['links', 'md', 'html'], 'type': 'string'}, {'type': 'null'}], 'default': None, 'description': "\n        The format of the output. Works only when parse parameter is false.\n            - 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.\n            - 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.\n            - html - Should be used sparingly only when you need the raw HTML structure, JavaScript code, or styling information.\n        "}, 'user_agent_type': {'anyOf': [{'enum': ['desktop', 'desktop_chrome', 'desktop_firefox', 'desktop_safari', 'desktop_edge', 'desktop_opera', 'mobile', 'mobile_ios', 'mobile_android', 'tablet'], 'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Device type and browser that will be used to determine User-Agent header value.'}}, 'additionalProperties': False}

{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}