MCP MeasureMCP Measure

索引已观测

oxylabs-mcp

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

我该使用它吗

质量与安全性

A
描述质量
97%
模式完整度
89%
命名质量
82%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

发现（1）

  • LOWTool 'ai_map' description lacks action verb在 ai_map 中

基于对工具定义和协议合规性的自动分析。

上下文开销

~4,914token 数（工具定义）
~5.5 KB典型响应大小
对注意力有显著影响（占 128k 上下文窗口的 3.84%）

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中：

{
  "mcpServers": {
    "oxylabs-mcp": {
      "command": "uvx",
      "args": [
        "oxylabs-mcp"
      ]
    }
  }
}

可运行的软件包

pypioxylabs-mcp0.9.1stdio

远程端点

https://mcp.oxylabs.io/mcpstreamable-http

它能做什么

工具清单

工具（10）

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢ai_crawler(url, user_prompt, output_format, schema, render_javascript, ...)

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.

输入模式

{
  "type": "object",
  "properties": {
    "url": {
      "description": "The URL from which crawling will be started.",
      "type": "string"
    },
    "user_prompt": {
      "description": "What information user wants to extract from the domain.",
      "type": "string"
    },
    "output_format": {
      "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.",
      "enum": [
        "json",
        "markdown",
        "csv",
        "toon"
      ],
      "type": "string"
    },
    "schema": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "The JSON schema to use for structured data extraction from the crawled pages. Only required if output_format is json, csv or toon."
    },
    "render_javascript": {
      "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.",
      "type": "boolean"
    },
    "return_sources_limit": {
      "default": 25,
      "description": "The maximum number of sources to return.",
      "maximum": 50,
      "type": "integer"
    },
    "geo_location": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Two letter ISO country code to use for the crawl proxy."
    }
  },
  "required": [
    "url",
    "user_prompt"
  ],
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢ai_scraper(url, output_format, schema, render_javascript, geo_location)

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.

输入模式

{
  "type": "object",
  "properties": {
    "url": {
      "description": "The URL to scrape",
      "type": "string"
    },
    "output_format": {
      "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.",
      "enum": [
        "json",
        "markdown",
        "csv",
        "toon"
      ],
      "type": "string"
    },
    "schema": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "The JSON schema to use for structured data extraction from the scraped page. Only required if output_format is json, csv or toon."
    },
    "render_javascript": {
      "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.",
      "type": "boolean"
    },
    "geo_location": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Two letter ISO country code to use for the scrape proxy."
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢ai_browser_agent(url, task_prompt, output_format, schema, geo_location)

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

输入模式

{
  "type": "object",
  "properties": {
    "url": {
      "description": "The URL to start the browser agent navigation from.",
      "type": "string"
    },
    "task_prompt": {
      "description": "What browser agent should do.",
      "type": "string"
    },
    "output_format": {
      "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.",
      "enum": [
        "json",
        "markdown",
        "html",
        "csv",
        "toon"
      ],
      "type": "string"
    },
    "schema": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "The schema to use for the scrape. Only required if output_format is json, csv or toon."
    },
    "geo_location": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Two letter ISO country code to use for the browser proxy."
    }
  },
  "required": [
    "url",
    "task_prompt"
  ],
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢ai_search(query, limit, render_javascript, return_content, geo_location)

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.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "description": "The query to search for.",
      "type": "string"
    },
    "limit": {
      "default": 10,
      "description": "Maximum number of results to return.",
      "maximum": 50,
      "type": "integer"
    },
    "render_javascript": {
      "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. ",
      "type": "boolean"
    },
    "return_content": {
      "default": false,
      "description": "Whether to return markdown content of the search results.",
      "type": "boolean"
    },
    "geo_location": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Two letter ISO country code to use for the search proxy."
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢generate_schema(user_prompt, app_name)

Generate a json schema in openapi format.

输入模式

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

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢ai_map(url, search_keywords, user_prompt, max_crawl_depth, render_javascript, ...)

Tool useful for mapping website's URLs.

输入模式

{
  "type": "object",
  "properties": {
    "url": {
      "description": "The URL from which URLs mapping will be started.",
      "type": "string"
    },
    "search_keywords": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "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."
    },
    "user_prompt": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "What kind of URLs user wants to find. Can be used together with 'search_keywords'."
    },
    "max_crawl_depth": {
      "default": 1,
      "description": "The maximum depth of the crawl.",
      "maximum": 5,
      "type": "integer"
    },
    "render_javascript": {
      "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.",
      "type": "boolean"
    },
    "limit": {
      "default": 25,
      "description": "The maximum number of URLs to return.",
      "maximum": 50,
      "type": "integer"
    },
    "geo_location": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Two letter ISO country code to use for the mapping proxy."
    },
    "allow_subdomains": {
      "default": false,
      "description": "Whether to map subdomains URLs as well.",
      "type": "boolean"
    },
    "allow_external_domains": {
      "default": false,
      "description": "Whether to include external domains URLs.",
      "type": "boolean"
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢universal_scraper(url, render, user_agent_type, geo_location, output_format)

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

输入模式

{
  "type": "object",
  "properties": {
    "url": {
      "description": "Website url to scrape.",
      "type": "string"
    },
    "render": {
      "anyOf": [
        {
          "const": "html",
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "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        ",
      "examples": [
        "html"
      ]
    },
    "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": null,
      "description": "Device type and browser that will be used to determine User-Agent header value."
    },
    "geo_location": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "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        ",
      "examples": [
        "US",
        "DE",
        "FR"
      ]
    },
    "output_format": {
      "anyOf": [
        {
          "enum": [
            "links",
            "md",
            "html"
          ],
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "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        "
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢google_search_scraper(query, parse, render, user_agent_type, start_page, ...)

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

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "description": "URL-encoded keyword to search for.",
      "type": "string"
    },
    "parse": {
      "default": true,
      "description": "Should result be parsed. If the result is not parsed, the output_format parameter is applied.",
      "type": "boolean"
    },
    "render": {
      "anyOf": [
        {
          "const": "html",
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "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        ",
      "examples": [
        "html"
      ]
    },
    "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": null,
      "description": "Device type and browser that will be used to determine User-Agent header value."
    },
    "start_page": {
      "default": 0,
      "description": "Starting page number.",
      "type": "integer"
    },
    "pages": {
      "default": 0,
      "description": "Number of pages to retrieve.",
      "type": "integer"
    },
    "limit": {
      "default": 0,
      "description": "Number of results to retrieve in each page.",
      "type": "integer"
    },
    "domain": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "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        ",
      "examples": [
        "uk",
        "us",
        "fr"
      ]
    },
    "geo_location": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "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        ",
      "examples": [
        "US",
        "DE",
        "FR"
      ]
    },
    "locale": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "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        ",
      "examples": [
        "en-US",
        "de-AT",
        "fr-FR"
      ]
    },
    "ad_mode": {
      "default": false,
      "description": "If true will use the Google Ads source optimized for the paid ads.",
      "type": "boolean"
    },
    "output_format": {
      "anyOf": [
        {
          "enum": [
            "links",
            "md",
            "html"
          ],
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "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        "
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢amazon_search_scraper(query, category_id, merchant_id, currency, parse, ...)

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.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "description": "Keyword to search for.",
      "type": "string"
    },
    "category_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Search for items in a particular browse node (product category)."
    },
    "merchant_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Search for items sold by a particular seller."
    },
    "currency": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Currency that will be used to display the prices.",
      "examples": [
        "USD",
        "EUR",
        "AUD"
      ]
    },
    "parse": {
      "default": true,
      "description": "Should result be parsed. If the result is not parsed, the output_format parameter is applied.",
      "type": "boolean"
    },
    "render": {
      "anyOf": [
        {
          "const": "html",
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "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        ",
      "examples": [
        "html"
      ]
    },
    "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": null,
      "description": "Device type and browser that will be used to determine User-Agent header value."
    },
    "start_page": {
      "default": 0,
      "description": "Starting page number.",
      "type": "integer"
    },
    "pages": {
      "default": 0,
      "description": "Number of pages to retrieve.",
      "type": "integer"
    },
    "domain": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "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        ",
      "examples": [
        "uk",
        "us",
        "fr"
      ]
    },
    "geo_location": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "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        ",
      "examples": [
        "US",
        "DE",
        "FR"
      ]
    },
    "locale": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "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        ",
      "examples": [
        "en-US",
        "de-AT",
        "fr-FR"
      ]
    },
    "output_format": {
      "anyOf": [
        {
          "enum": [
            "links",
            "md",
            "html"
          ],
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "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        "
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢amazon_product_scraper(query, autoselect_variant, currency, parse, render, ...)

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.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "description": "Keyword to search for.",
      "type": "string"
    },
    "autoselect_variant": {
      "default": false,
      "description": "To get accurate pricing/buybox data, set this parameter to true.",
      "type": "boolean"
    },
    "currency": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Currency that will be used to display the prices.",
      "examples": [
        "USD",
        "EUR",
        "AUD"
      ]
    },
    "parse": {
      "default": true,
      "description": "Should result be parsed. If the result is not parsed, the output_format parameter is applied.",
      "type": "boolean"
    },
    "render": {
      "anyOf": [
        {
          "const": "html",
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "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        ",
      "examples": [
        "html"
      ]
    },
    "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": null,
      "description": "Device type and browser that will be used to determine User-Agent header value."
    },
    "domain": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "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        ",
      "examples": [
        "uk",
        "us",
        "fr"
      ]
    },
    "geo_location": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "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        ",
      "examples": [
        "US",
        "DE",
        "FR"
      ]
    },
    "locale": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "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        ",
      "examples": [
        "en-US",
        "de-AT",
        "fr-FR"
      ]
    },
    "output_format": {
      "anyOf": [
        {
          "enum": [
            "links",
            "md",
            "html"
          ],
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "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        "
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}

输出模式

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

推荐提示词

search_research
Search for information about [topic] using oxylabs-mcp
预期工具： ai_search
find_specific
Find [specific item] using oxylabs-mcp
预期工具： ai_search

社区

评价此服务器

证据

最近观测

已验证未记录版本10 个工具
已验证未记录版本10 个工具
已验证未记录版本10 个工具