Can an AI agent sign up for ScrapingBee on its own?

No. Sign-up: needs a human. Only a web form with a visible reCAPTCHA v2 checkbox.

Can an AI agent use ScrapingBee?

Q: Can an AI agent pay for ScrapingBee?

Payment not reached. No 402/x402/MPP, no registry listings, no /.well-known/ucp. We paid nothing: no 402 asking for USDC. Paid plans $49-$3,599/mo bought in the dashboard; checkout not reachable without an account.

As of 12 Oct 2026, an AI agent can't use ScrapingBee on its own: reCAPTCHA checkbox on the sign-up form.

Level 1 · Needs a personAgents can't get in on their own.

Find: Some docs for agents: llms.txt and an MCP server.
Access: Can't sign up.
Use: Work not reached.
Pay: Payment not reached.
Leave: Leaving not reached.

To reach L2 · Gets in: let an agent sign up on its own.

With an account set up by a person: not measured yet.

What the levels mean

Visit ScrapingBee Follow changes

Driven 12 Oct 2026Same level in 2 drives in a rowRules of 15 Oct 2026Claim this page

Written and checked by our agents from this drive's record. How we write.

Who gets in

Agents on a serverStopped by a CAPTCHA on the sign-up form.
Signed agentsThe sign-up page opens. The CAPTCHA on the form stops them too.
Agents in a person's browserNot measured yet.

Sign-up page checked 12 Oct 2026. Signed agents: the ones Cloudflare verifies. Where agents come from

What an agent can do in ScrapingBee.

On its own

Read the tool's documentation pages written for AI agents
See the list of available tools without needing an account yet

What it can't, and why

Create an accountSign-up form has a checkbox only a human can tick
Get an access key or scrape any pageNeeds the account it could never create
Pay for a paid planPayment only happens inside the account dashboard, which it couldn't reach

Official server · its calls worked

Does ScrapingBee have an MCP server, and can an agent connect to it?

Yes. ScrapingBee has an official MCP server. The server is hosted, lists 18 tools and speaks the 25 Nov 2025 MCP spec.

A new agent can't get in on its own: in the drive of 12 Oct 2026, our agent stopped at sign up (it needs a person). Through the MCP server, 1 of our agent's 1 attempt worked.

What the drive found

API–OpenAPIMCP · officialCLISDKllms.txt–Webhooks–Sandbox

Payment not reached

Can an AI agent pay for ScrapingBee?

Payment not reached.

Payment tools on its MCP server on its own domain

No card needed to start.

What would let agents pay on their own

Accept x402 or MPP on your API. Answer an unpaid call with 402 and a payment challenge, so an agent pays per call or buys credits without an account or a card.Step-by-step guide
List your plans on Stripe Projects. Agents buy a plan with `stripe projects add`, paid with a token under a spend cap the owner sets (projects.dev).Step-by-step guide

No 402/x402/MPP, no registry listings, no /.well-known/ucp. We paid nothing: no 402 asking for USDC. Paid plans $49-$3,599/mo bought in the dashboard; checkout not reachable without an account.

Ways to pay checked 12 Oct 2026.

Not reached in this drive: the API key and deleting the account. Every checkpoint, in detail

For the team behind ScrapingBee.

Where agents stop in ScrapingBee today, and the fixes that get them further, highest impact first.

Stops at sign up

The fixes, highest impact first

Let verified agents sign upStep-by-step guide
Accept x402 or MPP on the APIStep-by-step guide
Move MCP server to the 28 Jul 2026 spec

2 more fixes

Publish an OpenAPI spec Step-by-step guide
Align MCP key error with docs

Claim it free and reply next to the result.
A Drive, $49: your private report, with where agents stop, the evidence and the fixes that move your level.
Fixed something? Order a Drive ($49) any time, or the Monthly drive ($29/month).

Get a Drive Claim it free

See the example report

Details

Your API, MCP server or CLI is the product? An Audit ($299) also checks every documented route, MCP tool and CLI command against your docs. Compare plans.

Already claimed it? Open it in your dashboard.

Rather not be driven? Block AgentDrivesAgent in robots.txt or write to us. We stop driving it ourselves; this page stays, with its date.

Embed the badge on your site

<a href="https://agentdrives.com/tools/scrapingbee" rel="nofollow"><img src="https://agentdrives.com/badge/scrapingbee.svg" alt="AgentDrives · Driven · L1 · Needs a person" height="24"></a>

Behind the level.

Our agent couldn't get into ScrapingBee, so the work, its reliability and the crash test aren't measured. The part scores are what it could judge from the outside.

Part scores · level history

Part scores

Agent-ready setup

llms.txt: found
OpenAPI: not found
MCP server: found
CLI: found

Not measured in this drive: Holds up, Docs match (part of an Audit).

Level history

6 Oct 2026L1Needs a person
12 Oct 2026L1Needs a person

For agents and builders.

The drive as data, every checkpoint and all 13 attempts.

How an agent connects · 4 tips

/api/tools/scrapingbee.json /tools/scrapingbee.mdMCP get_tool {"slug":"scrapingbee"}

Start at https://www.scrapingbee.com/llms.txt
Sign-up needs a human to tick a reCAPTCHA; ask for the key up front
MCP speaks 2025-11-25; use initialize, key in ?api_key=
Use fast_search before get_google_search_results; check Spb-cost headers for credits

Every checkpoint, in detail · 9 checkpoints

DocsHeadlessllms.txt with per-API text references; no OpenAPI; no markdown negotiation
Sign upNeeds a humanOnly a web form with a visible reCAPTCHA v2 checkbox.
VerifyNot reachedNo account: sign-up stopped at reCAPTCHA
KeyNot reachedAPI key only from the dashboard; no key API; CLI/MCP need an existing key
First callNot reachedNo key: usage API 400 'api_key Missing data for required field.'; MCP tools/call 'API key is missing'
First actionNot reachedNo key
PayNot reachedNo 402/x402/MPP, no registry listings, no /.well-known/ucp. We paid nothing: no 402 asking for USDC. Paid plans $49-$3,599/mo bought in the dashboard; checkout not reachable without an account.
CancelNot reachedNot tested: no plan or trial was started. Paid plans exist but checkout sits behind the account/reCAPTCHA wall, so cancel was not tested; pricing says 'Cancel anytime, no questions asked!' but no cancel API is documented.
DeleteNot reachedNo account was created; no delete API documented

The attempt log · 13 attempts

Attempt log
Capability	Route	Result	Evidence
Docs and agent discovery: llms.txt, robots, OpenAPI, markdown	api	done ✓	llms.txt 200 at https://www.scrapingbee.com/llms.txt with per-API .txt docs under /llms/; robots.txt 'User-agent: * Disallow:' no Content-Usage; /openapi.json 404; Accept: text/markdown on /documentation/ returns text/html; documentation.md 404
MCP server discover: server/discover on mcp.scrapingbee.com/mcp	mcp	done ✓	server/discover -> HTTP 400 JSON-RPC -32600 'Unsupported protocol version: 2026-07-28. Supported versions: 2024-11-05, 2025-03-26, 2025-06-18, 2025-11-25'; initialize offering 2026-07-28 -> protocolVersion 2025-11-25, serverInfo ScrapingBee 2.2.1, SSE reply
Cards and well-knowns: server-card, ai-catalog, agent-card, PRM, ucp, auth.md	api	done ✓	mcp/server-card 404, /.well-known/ai-catalog.json 404, agent-card.json 404, agent.json 404, oauth-protected-resource 404 on both hosts, /.well-known/ucp 404, /auth.md 404, /SKILL.md 404
Sign up: Find a headless/API sign-up route	none	blocked	llms.txt, CLI and MCP docs offer no account-creation API; only the web form at dashboard.scrapingbee.com/account/register (plus Google/GitHub login)
Sign up: Sign up via web form with the agent's inbox	browser	blocked	Submitted form; page answered 'recaptcha: The response parameter is missing.' A visible reCAPTCHA v2 'I'm not a robot' checkbox sits on the form (screenshot browser/shots/002.png)
Sign up: Ask a human to tick the reCAPTCHA	browser	blocked
Verify email: Verify sign-up email	none	blocked	No account created (sign-up stopped at reCAPTCHA)
Get API key: Get API key; scoped key via API/CLI	none	blocked	No account. Docs: key only from the dashboard; CLI 'scrapingbee auth' asks for an existing key (llms/cli.txt); MCP needs api_key (llms/remote-mcp.txt); no key-management API found in llms.txt index
First API call: Call usage API / MCP tool without a key	api	blocked	GET https://app.scrapingbee.com/api/v1/usage -> 400 {"errors":{"api_key":{"api_key":["Missing data for required field."]}}}; MCP tools/list works without key (18 tools) but tools/call get_scrapingbee_usage -> isError 'ScrapingBee API key is missing. Send it as an Authorization: Bearer <api_key> header.'
First real action: Scrape a page	api	blocked	GET /api/v1/?url=https://example.com without key -> 400 missing api_key; no account
Pay: Public pay probes: 402, registries, billing API, checkout, trial	api	done ✓	pay_probe.json: no 402 challenges, no x402/MPP subdomains (no such host), not in mpp.dev/Stripe Projects/Bazaar; /.well-known/ucp 404; no OpenAPI; llms docs mention no x402/MPP/Stripe; pricing page: Freelance $49/mo..Enterprise, 'Try ScrapingBee with 1,000 free API credits. Sign up No credit card required.' MCP tools fast_search/get_scrapingbee_usage are not payment tools (usage is read-only). pay_tx.json: refused, no 402 asking for USDC. Checkout not visible without an account.
Cancel plan: Cancel plan	none	skipped	not tested: no plan or trial was started. Pricing page says 'Cancel anytime, no questions asked!'; no cancel API documented
Delete account: Delete account	none	blocked	No account was created (sign-up stopped at reCAPTCHA); no account-delete API in docs

Also in Web scraping.

All of Web scraping, by level

FirecrawlL4Gets in on its ownScrapingBee vs Firecrawl
Browse AIL3Gets in on its ownScrapingBee vs Browse AI
ApifyL1Can't sign up on its ownScrapingBee vs Apify