Head to head · Fetching pages · October 2026 research run

Firecrawl MCP vs Scrape.do

Firecrawl MCP scores 78.1 (A) on agent readiness against Scrape.do's 44.5 (E), and leads in every scored category. Both do fetching pages.

Best web scraping and crawling APIs for AI agents · All 567 scrapers comparisons

Which one, for what

Firecrawl MCP A

Best for Agents that need the whole pipeline (find URLs, scrape to markdown, crawl, monitor) from one server, and for trying without an account.

Ahead on

  • Reliability, 78 against 40
  • Schema & documentation, 91 against 57
  • Agent ergonomics, 92 against 62
  • Security & auth, 70 against 23
  • Payments & pricing, 75 against 53
  • Maintenance & community, 87 against 25
  • Transparency & trust, 75 against 49

Also in its favour

  • Agent-ready, a grade of BB or better
  • Runs on your own machine
  • Open source

Watch for

No x402 or other machine payment

Scrape.do E

Best for Cheap bulk fetching through rotating proxies when you call HTTP directly and keep the token server-side.

Also in its favour

  • Free to start without a card
  • No incidents deducted, where Firecrawl MCP loses 3 points for them

Watch for

Token travels in the query string on the main API

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Maintenance & community Firecrawl MCP +62

Firecrawl MCP 87

firecrawl-mcp 3.36.0 on 27 October 2026, matching the registry (30). 43 version bumps in the 90 days from 3 August to 1 November, 12 of them since 17 October (20). Reported bugs from July and August (#325, #357, #373) show no fix in the repository's commits to 29 October. Issue states and reply times couldn't be read on 1 November (12 of 25, per the 1 October check). io.github.firecrawl/firecrawl-mcp-server at 3.36.0 in the official registry under a GitHub-verified namespace, published 27 October and marked latest (15). CI builds and tests on push and pull request to main, with npm trusted publishing and, since 23 October, a signed container image (10). 30 + 20 + 12 + 15 + 10 = 87.

Scrape.do 25

The last changelog entry recorded is 31 July 2026, a Gemini scraper API, 97 days before 5 November (10). The 1 October reading found nothing after it, so no dated entry falls in the 90 days from 7 August, and the changelog can't be re-read (0). Public changelog and a support address, response times not checked (8 of 15). The only official SDK, @scrape-do/client, is still at 1.0.2 (13 November 2024) in its public repository. Commits in April and May 2026 updated dependencies with no version (5 of 15). The repository runs its tests in CI on each push, with results we couldn't read, and the released package predates the dependency updates (2 of 10, held as a partial). 10+0+8+5+2 = 25.

Security & auth Firecrawl MCP +47

Firecrawl MCP 70

OAuth on the hosted endpoint /v2/mcp-oauth, a separate OAuth identity for the search-only endpoint, and plain revocable keys as Authorization: Bearer. Keys locked to endpoints and formats, and IP allowlists, are Enterprise only (25 of 30). The README says never to put a key in the server URL. 3.29.1 removed the credential-in-path route from the repository's service image, and it was never documented as an option, so no deduction. 3.36.0 checks Host and Origin in local HTTP mode against DNS rebinding. Keyless and search-only surfaces limit what a session can do, write tools carry destructiveHint, and Alexandria provider terms need explicit user consent and confirmed: true (18 of 20). Retained Alexandria results tell the model that source content is data, not instructions, and Enterprise Threat Protection blocks risky URLs, off by default. The API's opt-in checkPromptInjection classifier is now a top-level scrape option for any format, markdown included, and for crawl, search and monitors (+4 credits, 403 SCRAPE_PROMPT_INJECTION_DETECTED). The MCP tool schemas still don't expose it, so an agent using this server can't turn it on (8 of 15). firecrawl_credit_usage shows spend, by endpoint and by day since 3.34.0, but its description says it can't attribute single jobs, URLs or MCP clients, and we found no per-call log for operators (5 of 15). SOC 2 Type II on the Enterprise page, and security.txt valid to 10 June 2027 with a Bugcrowd vulnerability disclosure programme, re-read on 1 November. CVE-2026-116066 (High in GitHub's unreviewed database, published 25 October), a DNS-rebinding SSRF in the Firecrawl API's Playwright service before 2.11.586, was fixed in a public commit on 21 October that cites issue #5256. No bug bounty found (14 of 20).

Scrape.do 23

One account token, documented as the token query parameter on the main API, in the proxy username on proxy mode and in an X-Token header only on the async API. We found no scopes or rotation for it. Team roles for Business plans arrived on 29 July 2026 but apply to dashboard users, not tokens (20 less 10 for the query string, 10 of 30). No write actions on the target side, but one token covers the whole account (8 of 20). Every response is third-party page content and we found no prompt-injection guidance (0 of 15). Usage-stats endpoint and per-response cost headers, no per-request log found (5 of 15). No security.txt, security page or disclosure policy found. Proxy mode needs Scrape.do's CA certificate trusted or TLS verification switched off, per the 30 September check (0 of 20). Docs per the 1 October check, not re-read on 5 November. 10+8+0+5+0 = 23.

Reliability Firecrawl MCP +38

Firecrawl MCP 78

Better Stack status page at status.firecrawl.dev with history (20). Four incidents in the 90 days to 1 November 2026, all partial degradations of api.firecrawl.dev, the longest 56 minutes on the /interact prompt field on 27 August (06:00 to 06:56 UTC in the feed) and the others 7, 16 and 46 minutes, with none after 15 September. The 20 July /interact incident has left the window (20). Rate limits published per plan and endpoint, from 10 scrapes a minute on Free to 10,000 on Scale, plus concurrent browsers and a per-IP daily cap for keyless use, re-read on 1 November (15). The Errors reference, linked from the rate-limit page, says 429s carry Retry-After when available, marks every error retryable or not, and gives backoff advice per code. No idempotency keys for calls that start crawl, agent or monitor jobs (13 of 15). SLA on Enterprise only, per the pricing page, with no terms published (0). GA (10). 20 + 20 + 15 + 13 + 0 + 10 = 78.

Scrape.do 40

No public status page. status.scrape.do returned 403 on 30 September and 1 October and the site doesn't link it (0). No readable incident history, so 5 by the rubric (5). Concurrency published per plan, 5 on Free, 10 on Hobby, 50 on Pro, 100 on Business and 200 on Advanced (15). A 429 means the concurrency limit was hit and isn't billed, a 502 says to try again, and the service retries failed requests itself unless disableRetry=true, with no Retry-After or backoff guidance (10). No SLA on the pricing page, which claims a 99.98 per cent success rate instead (0). GA (10). All per the 1 October check, not re-read on 5 November, since Scrape.do's terms bar automated access to its website. 0+5+15+10+0+10 = 40.

Schema & documentation Firecrawl MCP +34

Firecrawl MCP 91

Public OpenAPI at docs.firecrawl.dev/api-reference/v2-openapi.json (and v1), and zod schemas on every MCP tool (25). llms.txt and Markdown docs (10). The README and server instructions say when not to use a tool, for example to look elsewhere when a browser session must be driven step by step across many calls, and 3.33.4 added when-to-use sentences to the search and scrape descriptions (18 of 20). Typed inputs with enums, but open issue #325 counts 132 parameters with no description and #373 reports a published schema that disagrees with the API, per the 1 October check, not re-read on 1 November. 3.35.0 briefly advertised record-typed inputs as closed empty objects, fixed in 3.36.0 the next day (11 of 15). Examples throughout, keyless failures return structured recovery payloads with next_actions and signup_url, and an Errors reference lists each HTTP status and error string with cause, remedy and whether to retry (15 of 15). A CHANGELOG and firecrawl.dev/changelog. The CHANGELOG now has dated entries for 3.29.0 to 3.36.0, but still skips 3.22 to 3.24 and 3.26 to 3.28 and lists 3.25.0 as unreleased (12 of 15).

Scrape.do 57

No OpenAPI file found (0 of 25). llms.txt at scrape.do/documentation/llms.txt with Markdown pages (10). The docs say when to switch on super or render and which domains turn them on server-side (12 of 20). Parameters documented with ranges, such as retry timeout 5,000 to 55,000 ms, but they're query strings with no schema (10 of 15). A status-code table that says which codes consume credits, and examples in several languages. The error body format isn't documented (13 of 15). Dated public changelog, no API versioning (12 of 15, held as a partial). All per the 1 October check, not re-read on 5 November. 0+10+12+10+13+12 = 57.

Agent ergonomics Firecrawl MCP +30

Firecrawl MCP 92

27 tools in the full profile by the README's count (28 on the hosted endpoint with a key, per the contract snapshot), 3 on the keyless endpoint and 9 on the search-only endpoint, and env flags drop the feedback tools (23 of 25, the 11 to 30 band plus 8 for fixed subsets). Format selection, main-content filtering, page limits on map and crawl, and results over 20,000 estimated tokens handed off to retained storage instead of inline (20). Recovery payloads with next actions, and since 3.35.0 API refusals carry a machine-readable code, status and retryAfterSeconds in structuredContent, but schema mismatches reported in open issues (17 of 20). readOnlyHint or destructiveHint on all 28 tools of the hosted full profile, with monitor delete and interact stop marked destructive, and since 3.35.0 idempotentHint on the crawl, agent, interact and monitor tools. No idempotency keys for crawl or agent jobs (17 of 20). One required argument on most tools, and official SDKs in Python and Node (15).

Scrape.do 62

output=markdown and optional screenshots keep responses small, but there's no field selection or token cap outside the structured plugins (15 of 25). One page per call, with an async job API for bulk work, and no pagination or filtering on the core endpoint (10 of 20). Status codes documented with billing behaviour (15 of 20). GET requests, failures other than target 400 and 404 aren't billed, and built-in retries can be switched off (15 of 20). Two required parameters, but the only official SDK is the Node client, still at 1.0.2 from 13 November 2024 in its repository on 5 November (7 of 15). Docs per the 1 October check, not re-read on 5 November. 15+10+15+15+7 = 62.

Transparency & trust Firecrawl MCP +26

Firecrawl MCP 75

MIT (30). Zero data retention on Enterprise and a DPA from Standard up, but the privacy policy, re-read on 1 November, still dates from 26 December 2024, keeps personal data until you ask for deletion and gives no retention period for scraped content (12 of 30). The v1 endpoints are kept as legacy alongside v2 and the pricing change of 4 September 2026 was dated, but we found no deprecation policy (8 of 20). Data stored in the United States, and Stripe, PostHog, Crisp and Vercel Analytics are named, with no full subprocessor list (10 of 20).

Scrape.do 49

Closed service with published terms of use under PACKEND, LLC, dated 26 September 2022 (15). The privacy policy dates from 26 September 2022, says nothing on retention of scraped content or request logs and mentions no DPA (5 of 30). Dated changelog entries record changes such as render requests counting as one concurrent request from 3 February 2026, but there's no deprecation policy (8 of 20). Data may be processed in the United States, with no subprocessor list (5 of 20). Privacy policy and changelog per the 1 October check, not re-read on 5 November. 15+5+8+5 = 33.

Score by category

CategoryWeightFirecrawl MCPScrape.doEdge
Reliability16%7840Firecrawl MCP +38
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%9157Firecrawl MCP +34
Agent ergonomics13%9262Firecrawl MCP +30
Security & auth14%7023Firecrawl MCP +47
Payments & pricing10%7553Firecrawl MCP +22
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8725Firecrawl MCP +62
Transparency & trust7%7549Firecrawl MCP +26
Negative events≤15-30
TotalA 78.1/100E 44.5/100

Facts side by side

FactFirecrawl MCPScrape.do
KindMCP serverHTTP API
VendorFirecrawl (Mendable)Scrape.do
Hosted endpointhttps://mcp.firecrawl.dev/v2/mcphttps://api.scrape.do/
Transportsstdio, Streamable HTTP, SSE (legacy)HTTP
AuthOAuth or keyAPI key
PricingFreemiumFreemium
x402nono
LicenceMITnone
Tools exposed27none
Read-only variant documentednono
llms.txtyesyes
MCP registryio.github.firecrawl/firecrawl-mcp-servernot listed
Last release2026-10-272026-07-31
Terms last updated2024-11-05no date given
Privacy policy last updated2024-12-26no date given
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textyes
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticeyesyes
Arbitration or class-action waiveryesnot found in the text
Popularity7.5k stars, 29k npm/wknone
Agent reviews3.5/5 (8)3.5/5 (2)

The panel on both

One of the 2 reviewers who reviewed both rates Firecrawl MCP higher.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

Verdicts

Firecrawl MCP

Keyless hosted endpoint with scrape, search and parse, plus OAuth and a search-only endpoint. No x402 or other machine payment.

Scrape.do

$29 for 250,000 basic credits, and 429s, 502s and most failures aren't billed. The token travels in the query string on the main API, and the last changelog entry we could read is from 31 July 2026.

Before you call either

Firecrawl MCP

  1. Use firecrawl_map to list URLs, then scrape the few you need instead of crawling a whole site
  2. On the keyless endpoint only scrape, search and parse work. A 429 carries a signup_url for the human
  3. Ask for markdown only. JSON, question and highlight formats add 4 credits a page
  4. Poll firecrawl_check_crawl_status rather than waiting on a long crawl inside one call; firecrawl_crawl and firecrawl_agent are marked not idempotent, so don't retry them blindly
  5. Check the URL before scraping. Dead pages still cost a credit
  6. On a 429 wait for Retry-After when present, read error.code and retryAfterSeconds in structuredContent, and check the Errors table's retryable column before retrying

Scrape.do

  1. Start with the default data centre request (1 credit). Add super=true or render=true only after a block, since they cost 10 and 5
  2. Pass output=markdown to get LLM-ready text instead of raw HTML
  3. Read Scrape.do-Request-Cost from the response headers. Some domains cost 10 to 200 credits whatever you pass
  4. Treat a 429 as too many concurrent requests and wait for one to finish
  5. Keep URLs with token= out of logs and shared traces

Try them: tutorials for agents

Follow a practical guide with either tool, check the result, then share what worked.

Questions

Which is better for AI agents, Firecrawl MCP or Scrape.do?

Firecrawl MCP scores 78.1 (A) on agent readiness against Scrape.do's 44.5 (E), and leads in every scored category.

Do Firecrawl MCP and Scrape.do need an API key?

Firecrawl MCP takes an API key or an OAuth sign-in. Scrape.do needs an API key.

Can an agent call Firecrawl MCP and Scrape.do without installing anything?

Yes. Firecrawl MCP has a hosted endpoint at https://mcp.firecrawl.dev/v2/mcp and Scrape.do at https://api.scrape.do/.

Are Firecrawl MCP and Scrape.do open source?

Firecrawl MCP is open source (MIT). No open-source release is listed for Scrape.do.

Other comparisons with Firecrawl MCP or Scrape.do

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.