Skip to content

ScrapingBee MCP server

com.scrapingbee/mcpscrapingbee.comstreamable-httpv2.2.1Scanned

Scrape any web page, search Google/Amazon/Walmart/YouTube and extract data via the ScrapingBee API.

18 tools: 1 do something that can't be undone, 2 change things and 15 only read.

Tools: 0 delete, 1 irreversible, 2 write, 15 read.
  • Reads private data · 1
  • Reads text others write · 10
  • Can send data out · 6
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here does something that can't be undone. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the ScrapingBee MCP server can do

The ScrapingBee MCP server is published by scrapingbee.com, a domain the MCP Registry verified. It has 18 tools. It can do things that cannot be undone, such as sending, paying or publishing (ask_chatgpt) and create or change data (2 tools: ask_gemini and extract_page_data), but cannot delete data. 15 tools only read.

1 tool reads private data (get_file); 10 tools bring in text other people can write (get_amazon_search_results, get_amazon_product_details, fast_search and 7 more); 6 tools can send data out of your system (ask_chatgpt, get_page_text, get_page_html and 3 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 11, 2026, version 2.2.1.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

18 tools

Can't be undone 1Claude Code: ask
  • ask_chatgptThis tool allows you to send a prompt to OpenAI's ChatGPT via ScrapingBee and get back the generated response.Can send data out1 finding

    Why it is in this group

    • The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • outboundThe description's first verb is "send": it sends or publishes something to other people.

    Findings

    • Warn

      The server marks "ask_chatgpt" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

      Matched text

      annotations: {"readOnlyHint":true}; The description's first verb is "send": a word for sending, and what is sent cannot be taken back.

      What this check looks for
    Description, as the server wrote it
    This tool allows you to send a prompt to OpenAI's ChatGPT via ScrapingBee and get back the generated response. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

    Annotations the server declares

    • readOnlyHint: true
Changes things 2Claude Code: ask
  • ask_geminiAsk Gemini through ScrapingBee and receive citation objects when available.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Ask Gemini through ScrapingBee and receive citation objects when available. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

    Annotations the server declares

    • readOnlyHint: true
  • extract_page_dataScrape a URL using ScrapingBee and extract specific data using CSS or XPath selectors.Reads text others writeCan send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe description's first sentence says "scrape": it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Scrape a URL using ScrapingBee and extract specific data using CSS or XPath selectors. Scope: one URL per call, with the result returned into the conversation. For many URLs, a whole site, output written to a file or directory, resumable jobs, or a scheduled re-run, use the ScrapingBee CLI instead — `scrapingbee scrape --input-file urls.txt --output-dir results`, `scrapingbee crawl URL --save-pattern ...`, `scrapingbee schedule --every`. This server has no batch, crawl, file-output or scheduling equivalent. Docs: https://www.scrapingbee.com/documentation/remote-mcp/

    Annotations the server declares

    • readOnlyHint: true
Only reads 15Show 15 read-only tools
  • get_amazon_pricingRetrieve current Amazon product pricing and seller offers for a given ASIN.No findings

    Why it is in this group

    • The name "get_amazon_pricing" says "get": a word for reading.
    Description, as the server wrote it
    Retrieve current Amazon product pricing and seller offers for a given ASIN. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

    Annotations the server declares

    • readOnlyHint: true
  • get_amazon_product_detailsScrape Amazon product details using ScrapingBee.Reads text others writeNo findings

    Why it is in this group

    • The name "get_amazon_product_details" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "scrape": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Scrape Amazon product details using ScrapingBee. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

    Annotations the server declares

    • readOnlyHint: true
  • get_amazon_search_resultsScrape Amazon search results using ScrapingBee.Reads text others writeNo findings

    Why it is in this group

    • The name "get_amazon_search_results" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "scrape": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Scrape Amazon search results using ScrapingBee. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

    Annotations the server declares

    • readOnlyHint: true
  • get_fileFetches a file from a URL and returns it in a format suitable for FastMcP.Reads private dataReads text others writeCan send data outNo findings

    Why it is in this group

    • The name "get_file" says "get": a word for reading.

    What it can reach

    • private-dataThe name "get_file" says "get" and "file": it reads files.
    • private-dataThe description's first sentence says "fetch" and "file": it reads files.
    • untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Fetches a file from a URL and returns it in a format suitable for FastMcP. This tool can be used to fetch any file type, including images, PDFs, etc. The framework will handle the encoding and packaging of the file. Scope: one URL per call, with the result returned into the conversation. For many URLs, a whole site, output written to a file or directory, resumable jobs, or a scheduled re-run, use the ScrapingBee CLI instead — `scrapingbee scrape --input-file urls.txt --output-dir results`, `scrapingbee crawl URL --save-pattern ...`, `scrapingbee schedule --every`. This server has no batch, crawl, file-output or scheduling equivalent. Docs: https://www.scrapingbee.com/documentation/remote-mcp/

    Annotations the server declares

    • readOnlyHint: true
  • get_google_search_resultsThis is a FALLBACK tool — use fast_search first for general web searches.No findings

    Why it is in this group

    • The name "get_google_search_results" says "get": a word for reading.
    Description, as the server wrote it
    This is a FALLBACK tool — use fast_search first for general web searches. Only use this tool when you need specialized search types that fast_search does not support: news, maps, Google Lens, shopping, image search, or Google AI mode. Scrape Google search results using ScrapingBee and return the results. This tool can scrape normal results, news results, maps results, search using google lens, shopping related results, image results, and get the result from Google's AI mode. It can even return the HTML along with the search results. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

    Annotations the server declares

    • readOnlyHint: true
  • get_page_htmlScrape a URL using ScrapingBee and return the page content in HTML.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "get_page_html" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe name "get_page_html" says "get" and "html": it reads web pages, which anyone can write.
    • untrusted-inputThe description's first sentence says "scrape": it reads web pages, which anyone can write.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Scrape a URL using ScrapingBee and return the page content in HTML. Scope: one URL per call, with the result returned into the conversation. For many URLs, a whole site, output written to a file or directory, resumable jobs, or a scheduled re-run, use the ScrapingBee CLI instead — `scrapingbee scrape --input-file urls.txt --output-dir results`, `scrapingbee crawl URL --save-pattern ...`, `scrapingbee schedule --every`. This server has no batch, crawl, file-output or scheduling equivalent. Docs: https://www.scrapingbee.com/documentation/remote-mcp/

    Annotations the server declares

    • readOnlyHint: true
  • get_page_textScrape a URL using ScrapingBee and return the page content in Markdown or Text format.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "get_page_text" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "scrape": it reads web pages, which anyone can write.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Scrape a URL using ScrapingBee and return the page content in Markdown or Text format. Scope: one URL per call, with the result returned into the conversation. For many URLs, a whole site, output written to a file or directory, resumable jobs, or a scheduled re-run, use the ScrapingBee CLI instead — `scrapingbee scrape --input-file urls.txt --output-dir results`, `scrapingbee crawl URL --save-pattern ...`, `scrapingbee schedule --every`. This server has no batch, crawl, file-output or scheduling equivalent. Docs: https://www.scrapingbee.com/documentation/remote-mcp/

    Annotations the server declares

    • readOnlyHint: true
  • get_scrapingbee_usageRead real-time credit and concurrency usage for the authenticated ScrapingBee account.No findings

    Why it is in this group

    • The name "get_scrapingbee_usage" says "get": a word for reading.
    Description, as the server wrote it
    Read real-time credit and concurrency usage for the authenticated ScrapingBee account. Note: This endpoint is rate-limited to 6 calls per minute and does not count against the account's concurrency limit. Returns: max_api_credit, used_api_credit, max_concurrency, current_concurrency, renewal_subscription_date.

    Annotations the server declares

    • readOnlyHint: true
  • get_screenshotScrape a URL using ScrapingBee and return it's screenshot.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "get_screenshot" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "scrape": it reads web pages, which anyone can write.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Scrape a URL using ScrapingBee and return it's screenshot. Scope: one URL per call, with the result returned into the conversation. For many URLs, a whole site, output written to a file or directory, resumable jobs, or a scheduled re-run, use the ScrapingBee CLI instead — `scrapingbee scrape --input-file urls.txt --output-dir results`, `scrapingbee crawl URL --save-pattern ...`, `scrapingbee schedule --every`. This server has no batch, crawl, file-output or scheduling equivalent. Docs: https://www.scrapingbee.com/documentation/remote-mcp/

    Annotations the server declares

    • readOnlyHint: true
  • get_walmart_product_detailsScrape Walmart product details using ScrapingBee.Reads text others writeNo findings

    Why it is in this group

    • The name "get_walmart_product_details" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "scrape": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Scrape Walmart product details using ScrapingBee. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

    Annotations the server declares

    • readOnlyHint: true
  • get_walmart_search_resultsScrape Walmart search results using ScrapingBee.Reads text others writeNo findings

    Why it is in this group

    • The name "get_walmart_search_results" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "scrape": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Scrape Walmart search results using ScrapingBee. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

    Annotations the server declares

    • readOnlyHint: true
  • get_youtube_search_resultsSearch YouTube and return structured results.No findings

    Why it is in this group

    • The name "get_youtube_search_results" says "get": a word for reading.
    Description, as the server wrote it
    Search YouTube and return structured results. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

    Annotations the server declares

    • readOnlyHint: true
  • get_youtube_video_metadataFetch structured metadata for a YouTube video including title, description, views, likes, channel info, and technical details.No findings

    Why it is in this group

    • The name "get_youtube_video_metadata" says "get": a word for reading.
    Description, as the server wrote it
    Fetch structured metadata for a YouTube video including title, description, views, likes, channel info, and technical details. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

    Annotations the server declares

    • readOnlyHint: true
  • get_youtube_video_subtitlesRetrieve subtitles for one YouTube video.No findings

    Why it is in this group

    • The name "get_youtube_video_subtitles" says "get": a word for reading.
    Description, as the server wrote it
    Retrieve subtitles for one YouTube video. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

    Annotations the server declares

    • readOnlyHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

60 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write10
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out6
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__scrapingbee__get_file"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:46 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
4
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://mcp.scrapingbee.com/.well-known/oauth-protected-resource/mcp
Authorization servers
https://mcp.scrapingbee.com
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 4 tools that change things (2 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.scrapingbee.com/mcp: tools/list returned 18 tools to an anonymous client, including ask_chatgpt (irreversible), get_screenshot (irreversible), ask_gemini (write), extract_page_data (write)

    What this check looks for

Posture changes

  1. Nov 20, 2026
    • Tools that change things, listed without credentials: 3 to 4
  2. Nov 13, 2026
    • RFC 9728 protected resource metadata: none to https://mcp.scrapingbee.com/.well-known/oauth-protected-resource/mcp
    • Authorization servers: none to https://mcp.scrapingbee.com
    • Dynamic client registration: not observed to yes
    • Client ID metadata documents: not observed to no

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "ask_chatgpt" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

    Matched text

    annotations: {"readOnlyHint":true}; The description's first verb is "send": a word for sending, and what is sent cannot be taken back.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. Tools that change things, listed without credentials: 3 -> 4.View diff
    • Tools that change things, listed without credentials: 3 to 4
  2. PostureRemote posture changed. RFC 9728 protected resource metadata: none -> https://mcp.scrapingbee.com/.well-known/oauth-protected-resource/mcp; Authorization servers: none -> https://mcp.scrapingbee.com; Dynamic client registration: not observe…View diff
    • RFC 9728 protected resource metadata: none to https://mcp.scrapingbee.com/.well-known/oauth-protected-resource/mcp
    • Authorization servers: none to https://mcp.scrapingbee.com
    • Dynamic client registration: not observed to yes
    • Client ID metadata documents: not observed to no
  3. Tools18 changed.~18 changedView diff

Install

Pinned to version 2.2.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http scrapingbee https://mcp.scrapingbee.com/mcp --header 'Authorization: <your-authorization>'
claude mcp add --transport http scrapingbee https://mcp.scrapingbee.com/mcp --header 'Authorization: <your-authorization>'

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__scrapingbee__get_amazon_search_results",
      "mcp__scrapingbee__get_amazon_product_details",
      "mcp__scrapingbee__get_amazon_pricing",
      "mcp__scrapingbee__fast_search",
      "mcp__scrapingbee__get_google_search_results",
      "mcp__scrapingbee__get_scrapingbee_usage",
      "mcp__scrapingbee__get_walmart_search_results",
      "mcp__scrapingbee__get_walmart_product_details",
      "mcp__scrapingbee__get_youtube_search_results",
      "mcp__scrapingbee__get_youtube_video_metadata",
      "mcp__scrapingbee__get_youtube_video_subtitles"
    ],
    "ask": [
      "mcp__scrapingbee__ask_chatgpt",
      "mcp__scrapingbee__ask_gemini",
      "mcp__scrapingbee__get_page_text",
      "mcp__scrapingbee__get_page_html",
      "mcp__scrapingbee__extract_page_data",
      "mcp__scrapingbee__get_screenshot",
      "mcp__scrapingbee__get_file"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as scrapingbee. Review it before you use it.

Capability tags behind 11 rules
  • mcp__scrapingbee__get_amazon_search_results untrusted-input
  • mcp__scrapingbee__get_amazon_product_details untrusted-input
  • mcp__scrapingbee__ask_chatgpt outbound
  • mcp__scrapingbee__fast_search untrusted-input
  • mcp__scrapingbee__get_page_text untrusted-input, outbound
  • mcp__scrapingbee__get_page_html untrusted-input, outbound
  • mcp__scrapingbee__extract_page_data untrusted-input, outbound
  • mcp__scrapingbee__get_screenshot untrusted-input, outbound
  • mcp__scrapingbee__get_file private-data, untrusted-input, outbound
  • mcp__scrapingbee__get_walmart_search_results untrusted-input
  • mcp__scrapingbee__get_walmart_product_details untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/com.scrapingbee/mcp/verify?hash=8cc264a5c59aca215ff03832bacca8db23dcaab8afbd30bcff3f1164eace552b" | jq -e '.changed == false'

Pinned hash 8cc264a5c59a, from Nov 11, 2026, 01:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.scrapingbee/mcp/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.scrapingbee/mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/com.scrapingbee/mcp.svg)](https://radar.anlyon.com/servers/com.scrapingbee/mcp)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:02 UTC.

ScrapingBee MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the ScrapingBee MCP server safe?

No scan can promise that. What its definitions show: 18 tools, 3 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the ScrapingBee MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the ScrapingBee MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: ask_chatgpt.

What tools does the ScrapingBee MCP server have?

18 tools: 1 irreversible, 2 write, 15 read. ask_chatgpt, ask_gemini, extract_page_data, get_amazon_search_results, get_amazon_product_details, get_amazon_pricing, fast_search, get_google_search_results and 10 more.

Does the ScrapingBee MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the ScrapingBee MCP server send data to outside services?

6 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): ask_chatgpt, get_page_text, get_page_html, extract_page_data, get_screenshot and get_file.

Has the ScrapingBee MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 11, 2026. Every change is on this page and in its Atom feed.