MCP MeasureMCP Measure

インデックス観測済み

ScrapingBot

Public web data for AI agents: scrape any page, plus Google, TikTok, Instagram and Amazon as JSON.

使うべきか

品質と安全性

A
説明の品質
93%
スキーマの完全性
79%
命名の品質
83%
ポイズニングのリスク
100%
権限の一致
100%
プロトコルへの準拠
100%

検出事項（4）

  • LOWTool 'getScrapeJob' description lacks action verbgetScrapeJob 内
  • LOWTool 'tiktokComments' description lacks action verbtiktokComments 内
  • LOWTool 'amazonProduct' description lacks action verbamazonProduct 内
  • LOWTool 'amazonRankings' description lacks action verbamazonRankings 内

ツール定義とプロトコルへの準拠に関する自動分析に基づいています。

コンテキストコスト

~4,141トークン数（ツール定義）
~1.4 KB一般的なレスポンスサイズ
注意への影響は大きい（128k コンテキストの 3.24%）

これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。

インストール

ワンクリックインストール

これを `claude_desktop_config.json` ファイルに追加してください:

{
  "mcpServers": {
    "scrapingbot": {
      "url": "https://scrapingbot.io/api/mcp"
    }
  }
}

リモートエンドポイント

https://scrapingbot.io/api/mcpstreamable-http

できること

ツール一覧

ツール（23）

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢listCapabilities

List every ScrapingBot tool, the API routes behind them and their parameters. Free.

入力スキーマ

{
  "type": "object",
  "properties": {}
}
🟢scrapeWebsite(url, render_js, stealth_proxy, premium_proxy, wait, ...)

Fetch any public web page and return its content as markdown (format: "html" for the raw HTML). 1 credit; render_js (pages built with JavaScript) 5; premium_proxy 10; stealth_proxy 75. screenshot: true attaches a screenshot image.

入力スキーマ

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "format": "uri"
    },
    "render_js": {
      "type": "boolean"
    },
    "stealth_proxy": {
      "type": "boolean"
    },
    "premium_proxy": {
      "type": "boolean"
    },
    "wait": {
      "type": "integer",
      "minimum": 0,
      "maximum": 45000
    },
    "wait_for": {
      "type": "string",
      "minLength": 1
    },
    "wait_browser": {
      "type": "string",
      "enum": [
        "load",
        "domcontentloaded",
        "networkidle0",
        "networkidle2"
      ]
    },
    "cookies": {
      "type": "string"
    },
    "screenshot": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "string",
          "const": "fullPage"
        }
      ]
    },
    "block_ads": {
      "type": "boolean"
    },
    "block_resources": {
      "type": "boolean"
    },
    "capture_runtime_issues": {
      "type": "boolean"
    },
    "timeout": {
      "type": "integer",
      "minimum": 1,
      "maximum": 120000
    },
    "format": {
      "type": "string",
      "enum": [
        "markdown",
        "html"
      ],
      "description": "Page content as markdown (default, compact and readable) or the raw HTML"
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢extractStructuredData(url, render_js, stealth_proxy, premium_proxy, wait, ...)

Fetch a web page and have AI pull out exactly the fields you want, as JSON. Pass ai_query (plain English, e.g. "title, price and stock") or ai_schema ({"field": "description"}). The page cost plus 5 credits.

入力スキーマ

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "format": "uri"
    },
    "render_js": {
      "type": "boolean"
    },
    "stealth_proxy": {
      "type": "boolean"
    },
    "premium_proxy": {
      "type": "boolean"
    },
    "wait": {
      "type": "integer",
      "minimum": 0,
      "maximum": 45000
    },
    "wait_for": {
      "type": "string",
      "minLength": 1
    },
    "wait_browser": {
      "type": "string",
      "enum": [
        "load",
        "domcontentloaded",
        "networkidle0",
        "networkidle2"
      ]
    },
    "cookies": {
      "type": "string"
    },
    "screenshot": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "string",
          "const": "fullPage"
        }
      ]
    },
    "block_ads": {
      "type": "boolean"
    },
    "block_resources": {
      "type": "boolean"
    },
    "capture_runtime_issues": {
      "type": "boolean"
    },
    "timeout": {
      "type": "integer",
      "minimum": 1,
      "maximum": 120000
    },
    "ai_query": {
      "type": "string",
      "minLength": 1
    },
    "ai_schema": {
      "anyOf": [
        {
          "type": "string",
          "minLength": 1
        },
        {
          "type": "object",
          "additionalProperties": {}
        }
      ]
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢getScrapeJob(job_id)

Look up an earlier scrape by the job_id it returned. Free.

入力スキーマ

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string",
      "minLength": 1
    }
  },
  "required": [
    "job_id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢pollJobUntilDone(job_id, timeout_ms, poll_interval_ms)

Wait for a scrape job to finish, then return it. Free.

入力スキーマ

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string",
      "minLength": 1
    },
    "timeout_ms": {
      "type": "integer",
      "minimum": 1000,
      "maximum": 300000
    },
    "poll_interval_ms": {
      "type": "integer",
      "minimum": 250,
      "maximum": 30000
    }
  },
  "required": [
    "job_id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢runBrowserScenario(url, render_js, stealth_proxy, premium_proxy, wait, ...)

Open a page in a real browser, run steps such as click, fill, scroll and wait, then return the resulting page as markdown. js_scenario: {"instructions": [{"fill": ["#q", "shoes"]}, {"click": "#go"}, {"wait": 1000}]}. From 5 credits.

入力スキーマ

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "format": "uri"
    },
    "render_js": {
      "type": "boolean"
    },
    "stealth_proxy": {
      "type": "boolean"
    },
    "premium_proxy": {
      "type": "boolean"
    },
    "wait": {
      "type": "integer",
      "minimum": 0,
      "maximum": 45000
    },
    "wait_for": {
      "type": "string",
      "minLength": 1
    },
    "wait_browser": {
      "type": "string",
      "enum": [
        "load",
        "domcontentloaded",
        "networkidle0",
        "networkidle2"
      ]
    },
    "cookies": {
      "type": "string"
    },
    "screenshot": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "string",
          "const": "fullPage"
        }
      ]
    },
    "block_ads": {
      "type": "boolean"
    },
    "block_resources": {
      "type": "boolean"
    },
    "capture_runtime_issues": {
      "type": "boolean"
    },
    "timeout": {
      "type": "integer",
      "minimum": 1,
      "maximum": 120000
    },
    "format": {
      "type": "string",
      "enum": [
        "markdown",
        "html"
      ],
      "description": "Page content as markdown (default, compact and readable) or the raw HTML"
    },
    "js_scenario": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "object",
            "additionalProperties": {}
          }
        },
        {
          "$ref": "#/properties/js_scenario/anyOf/0/items"
        }
      ]
    }
  },
  "required": [
    "url",
    "js_scenario"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢googleSearch(q, type, gl, hl, autocorrect, ...)

Google results as JSON: web (default), images, videos, news, shopping, places or maps (type), for any country (gl) and language (hl). Places and maps results include a cid for googleReviews. 10 credits.

入力スキーマ

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "minLength": 1
    },
    "type": {
      "type": "string",
      "enum": [
        "search",
        "images",
        "videos",
        "news",
        "shopping",
        "places",
        "maps"
      ],
      "description": "What to search: web results (default), images, videos, news, shopping, places or maps."
    },
    "gl": {
      "type": "string",
      "minLength": 2,
      "maxLength": 8
    },
    "hl": {
      "type": "string",
      "minLength": 2,
      "maxLength": 8
    },
    "autocorrect": {
      "type": "boolean"
    },
    "num": {
      "anyOf": [
        {
          "type": "integer",
          "minimum": 1,
          "maximum": 100
        },
        {
          "type": "string",
          "minLength": 1
        }
      ]
    },
    "page": {
      "anyOf": [
        {
          "type": "integer",
          "minimum": 1
        },
        {
          "type": "string",
          "minLength": 1
        }
      ]
    },
    "tbs": {
      "type": "string",
      "minLength": 1
    },
    "ll": {
      "type": "string",
      "minLength": 1,
      "description": "Maps/places viewport, e.g. @30.27,-97.74,12z"
    },
    "sortBy": {
      "type": "string",
      "minLength": 1
    }
  },
  "required": [
    "q"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢googleReviews(cid, fid, placeId, sortBy, nextPageToken, ...)

Reviews of a place from Google Maps, by the cid, fid or placeId in a googleSearch places or maps result. sortBy newest, mostRelevant, highestRating or lowestRating; pass nextPageToken for more. 10 credits.

入力スキーマ

{
  "type": "object",
  "properties": {
    "cid": {
      "type": "string",
      "minLength": 1
    },
    "fid": {
      "type": "string",
      "minLength": 1
    },
    "placeId": {
      "type": "string",
      "minLength": 1
    },
    "sortBy": {
      "type": "string",
      "enum": [
        "mostRelevant",
        "newest",
        "highestRating",
        "lowestRating"
      ]
    },
    "nextPageToken": {
      "type": "string",
      "minLength": 1
    },
    "gl": {
      "type": "string",
      "minLength": 2,
      "maxLength": 8
    },
    "hl": {
      "type": "string",
      "minLength": 2,
      "maxLength": 8
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢instagramUser(username, user_id, url)

An Instagram profile: bio, follower, following and post counts, links and the numeric user id other tools need. Pass one of username, user_id or url. 5 credits.

入力スキーマ

{
  "type": "object",
  "properties": {
    "username": {
      "type": "string",
      "minLength": 1
    },
    "user_id": {
      "anyOf": [
        {
          "type": "string",
          "minLength": 1
        },
        {
          "type": "integer",
          "exclusiveMinimum": 0
        }
      ]
    },
    "url": {
      "type": "string",
      "format": "uri"
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢instagramSearch(keyword, search_type)

Search Instagram accounts, hashtags, places or posts (search_type), or everything at once (global). 5 credits.

入力スキーマ

{
  "type": "object",
  "properties": {
    "keyword": {
      "type": "string",
      "minLength": 1
    },
    "search_type": {
      "type": "string",
      "enum": [
        "users",
        "hashtags",
        "places",
        "global",
        "posts"
      ]
    }
  },
  "required": [
    "keyword",
    "search_type"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢instagramMedia(mode, user_id, shortcode, url, code_or_id_or_url, ...)

Instagram content by mode: an account's posts, reels or tagged posts (user_id), one post by shortcode or url, a post's comments, the replies to a comment (comment_id), or an account's active stories (username). 5 credits.

入力スキーマ

{
  "type": "object",
  "properties": {
    "mode": {
      "type": "string",
      "enum": [
        "user_posts",
        "tagged_posts",
        "reels",
        "media_by_shortcode",
        "media_by_url",
        "comments",
        "comment_replies",
        "stories"
      ]
    },
    "user_id": {
      "anyOf": [
        {
          "type": "string",
          "minLength": 1
        },
        {
          "type": "integer",
          "exclusiveMinimum": 0
        }
      ]
    },
    "shortcode": {
      "type": "string",
      "minLength": 1
    },
    "url": {
      "type": "string",
      "format": "uri"
    },
    "code_or_id_or_url": {
      "type": "string",
      "minLength": 1
    },
    "media_id": {
      "anyOf": [
        {
          "type": "string",
          "minLength": 1
        },
        {
          "type": "integer",
          "exclusiveMinimum": 0
        }
      ]
    },
    "comment_id": {
      "type": "string",
      "minLength": 1,
      "description": "Parent comment id (comment_replies)"
    },
    "username": {
      "type": "string",
      "minLength": 1,
      "description": "Username (stories)"
    },
    "count": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 100
    },
    "end_cursor": {
      "type": "string",
      "minLength": 1
    },
    "pagination_token": {
      "type": "string",
      "minLength": 1
    }
  },
  "required": [
    "mode"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢instagramFollowers(user_id, direction, query, max_id)

List or search an Instagram account's followers or following, by numeric user_id from instagramUser. query searches the whole list; max_id pages. For very large accounts Instagram shows only about 50 recent followers, so use query to find someone. 5 credits.

入力スキーマ

{
  "type": "object",
  "properties": {
    "user_id": {
      "type": "string",
      "pattern": "^\\d+$",
      "description": "Numeric user id (from instagramUser)"
    },
    "direction": {
      "type": "string",
      "enum": [
        "followers",
        "following"
      ]
    },
    "query": {
      "type": "string",
      "minLength": 1,
      "description": "Search the list by username or name"
    },
    "max_id": {
      "type": "string",
      "minLength": 1,
      "description": "next_max_id from the previous page"
    }
  },
  "required": [
    "user_id",
    "direction"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢tiktokVideo(url)

A TikTok video's stats, caption, author, sound and download links, by video URL. 1 credit.

入力スキーマ

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "format": "uri"
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢tiktokUser(unique_id, include_posts)

A TikTok profile by username: bio, counts, verified badge and numeric user id; include_posts returns the latest videos instead. 1 credit.

入力スキーマ

{
  "type": "object",
  "properties": {
    "unique_id": {
      "type": "string",
      "minLength": 1
    },
    "include_posts": {
      "type": "boolean"
    }
  },
  "required": [
    "unique_id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢tiktokSearch(query, search_type, count, cursor, search_id)

Search TikTok creators (search_type: users) or videos (videos) by keyword. Videos page: for page 2 onward pass the previous response's data.cursor as cursor and its data.searchId as search_id. Users search returns a single page and ignores cursor. 1 credit.

入力スキーマ

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1
    },
    "search_type": {
      "type": "string",
      "enum": [
        "users",
        "videos"
      ]
    },
    "count": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 100
    },
    "cursor": {
      "anyOf": [
        {
          "type": "integer",
          "minimum": 0
        },
        {
          "type": "string",
          "minLength": 1
        }
      ],
      "description": "Videos only: the previous response's data.cursor, for the next page"
    },
    "search_id": {
      "type": "string",
      "minLength": 1,
      "description": "Videos only: the previous response's data.searchId; required with cursor for page 2 onward"
    }
  },
  "required": [
    "query",
    "search_type"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢tiktokComments(url, video_id, comment_id, count, cursor)

Comments on a TikTok video (url), or the replies to one comment (comment_id plus the video url or video_id). 1 credit.

入力スキーマ

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "Video URL (required for comments)"
    },
    "video_id": {
      "type": "string",
      "minLength": 1,
      "description": "Video id (replies only; or pass url)"
    },
    "comment_id": {
      "type": "string",
      "minLength": 1,
      "description": "Set to fetch the replies to this comment"
    },
    "count": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    },
    "cursor": {
      "type": "integer",
      "minimum": 0
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢tiktokFollowers(user_id, direction, count)

A TikTok account's followers or the accounts it follows, by numeric user_id (data.user.id from tiktokUser). Up to 50. 1 credit.

入力スキーマ

{
  "type": "object",
  "properties": {
    "user_id": {
      "type": "string",
      "pattern": "^\\d+$",
      "description": "Numeric user id (data.user.id from tiktokUser)"
    },
    "direction": {
      "type": "string",
      "enum": [
        "followers",
        "following"
      ]
    },
    "count": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    }
  },
  "required": [
    "user_id",
    "direction"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢amazonSearch(query, page, department)

Search Amazon US products by keyword: title, price, rating, Prime and photo for each. page for more. 10 credits.

入力スキーマ

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1
    },
    "page": {
      "anyOf": [
        {
          "type": "integer",
          "minimum": 1,
          "maximum": 100
        },
        {
          "type": "string",
          "minLength": 1
        }
      ]
    },
    "department": {
      "type": "string",
      "minLength": 1
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢amazonProduct(asin)

Everything on an Amazon product page by ASIN: price, rating, availability, bullet points, specifications, photos and variations. 10 credits.

入力スキーマ

{
  "type": "object",
  "properties": {
    "asin": {
      "type": "string",
      "minLength": 1
    }
  },
  "required": [
    "asin"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢amazonProducts(asins)

Full details for up to 20 ASINs in one call, the same as amazonProduct for each. 10 credits per product returned; ASINs that fail are free.

入力スキーマ

{
  "type": "object",
  "properties": {
    "asins": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1
      },
      "minItems": 1,
      "maxItems": 20,
      "description": "Up to 20 ASINs; 10 credits per product returned"
    }
  },
  "required": [
    "asins"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢amazonSuggestions(query, department, limit)

The suggestions Amazon shows as a shopper types: useful for keyword research. 10 credits.

入力スキーマ

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1,
      "description": "What a shopper has typed so far"
    },
    "department": {
      "type": "string",
      "minLength": 1,
      "description": "Search alias such as aps, electronics, stripbooks"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 20
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢amazonRankings(list, category, page)

Amazon's Best Sellers or New Releases for a department, in rank order, with price and rating. 10 credits.

入力スキーマ

{
  "type": "object",
  "properties": {
    "list": {
      "type": "string",
      "enum": [
        "best_sellers",
        "new_releases"
      ]
    },
    "category": {
      "type": "string",
      "enum": [
        "electronics",
        "pc",
        "wireless",
        "videogames",
        "books",
        "toys-and-games",
        "home-garden",
        "kitchen",
        "appliances",
        "beauty",
        "hpc",
        "grocery",
        "fashion",
        "sporting-goods",
        "pet-supplies",
        "baby-products",
        "automotive",
        "office-products",
        "arts-crafts",
        "musical-instruments"
      ],
      "description": "Amazon department slug"
    },
    "page": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100
    }
  },
  "required": [
    "list",
    "category"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢providerRequest(provider, endpoint, params)

Call any Google, Instagram, TikTok or Amazon endpoint by path, for the few the other tools do not cover (listCapabilities lists them). Costs the same as that API.

入力スキーマ

{
  "type": "object",
  "properties": {
    "provider": {
      "type": "string",
      "enum": [
        "google",
        "instagram",
        "tiktok",
        "amazon"
      ]
    },
    "endpoint": {
      "type": "string",
      "minLength": 1
    },
    "params": {
      "type": "object",
      "additionalProperties": {}
    }
  },
  "required": [
    "provider",
    "endpoint"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

コミュニティ

このサーバーを評価する

エビデンス

最近の観測

検証済みバージョンは記録されていませんツール 23 件