Head to head · Web search · October 2026 research run

Firecrawl MCP vs ScrapeGraphAI

Firecrawl MCP scores 78.1 (A) on agent readiness against ScrapeGraphAI's 64.8 (B), and leads in 6 of 7 scored categories. ScrapeGraphAI leads on payments & pricing. Both do web search.

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 49
  • Agent ergonomics, 92 against 72
  • Security & auth, 70 against 44
  • Maintenance & community, 87 against 40
  • Transparency & trust, 75 against 61

Also in its favour

  • Agent-ready, a grade of BB or better
  • Runs on your own machine
  • Open source
  • Rated higher by the reviewer agents, 3.5 against 3.0 out of 5

Watch for

No x402 or other machine payment

ScrapeGraphAI B

Best for LLM pipelines that want prompt-to-JSON extraction and for agents that must pay with a wallet.

Ahead on

  • Payments & pricing, 100 against 75

Also in its favour

  • No incidents deducted, where Firecrawl MCP loses 3 points for them

Watch for

Rate limits differ between docs pages (10, 100, 500 and 5,000 a minute against 5, 30 and 100)

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 +47

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.

ScrapeGraphAI 40

The newest changelog entry is still v3.5.0 of 30 July 2026 and the newest scrapegraph-py tag v2.3.2 of 31 July, 94 and 93 days before 1 November. scrapegraph-js has no tag after v2.0.1 (April) and its last commit is 3 August, and just-scrape has no tag and no commit after 24 June. Inside 180 days (10, 20 before, cause time). Nothing dated in the 90 days from 3 August, since the 6 and 30 July entries and the 30 and 31 July SDK tags left the window (0, 20 before, cause time). Public changelog and SDK repositories, issue replies not checked (8 of 25). Current Python SDK. The JavaScript SDK's last tag is v2.0.1 from April, with commits to 3 August (12 of 15). The Python SDK runs CI, CodeQL and dependency review (10). 10 + 0 + 8 + 12 + 10 = 40.

Reliability Firecrawl MCP +29

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.

ScrapeGraphAI 49

openstatus page at scrapegraphapi.openstatus.dev. On 1 November its page data lists no monitors, components or component groups, unchanged since it was created on 26 November 2024, and the site's own /api-status page shows v1 service names with a fixed uptime figure. A public page without component history, so half the line (10 of 20, 20 before). The events page says "No reports found for this status page", but with no monitor or component on it since it was created, before the v2 API, the page holds no history of this API at all. The clean-record reading this run gives a page that has never posted an incident (quicken-simplifi, outline, linkup) rests on pages that watch named components, so here it is read as no history we could read (5 of 30, 10 before when only seven days were readable). Rate limits published, but the rate-limits page and the pricing page give 10, 100, 500 and 5,000 a minute while the troubleshooting page gives 5, 30 and 100, re-read on 1 November (12 of 15). 429 documented with a rate_limit_exceeded body and exponential backoff examples (1, 2, 4 seconds), but no Retry-After and no idempotency keys (12 of 15). No SLA found. The pricing page lists an "SLA guarantee" on Enterprise with no terms or figure (0). v2 is GA (10). 10 + 5 + 12 + 12 + 0 + 10 = 49.

Security & auth Firecrawl MCP +26

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).

ScrapeGraphAI 44

OAuth 2.1 on the hosted MCP (Google sign-in, PKCE S256, dynamic client registration) with no scopes documented, and one API key per account that can be regenerated, with no scopes, expiry or second key (22 of 30). crawl_delete and monitor_delete sit next to read tools with no read-only mode or confirmation found (5 of 20). Scrape and extract return third-party content, and extract runs an LLM over that content, with no prompt-injection guidance in the MCP page or docs index (0 of 15). history_list, history_get and GET /api/history show each past request (12 of 15). The pricing page, read on 1 November, says "All requests are SOC 2 Type II compliant", and the site footer carries a SOC 2 Type 2 badge. security.txt answers 404, and no disclosure policy or bug bounty was found. A SOC 2 claim with no report, trust centre or disclosure route takes 5, as zeroentropy's pricing-page SOC 2 Type II claim and mandl-cooper's claim with no report (5), below coinmarketcap-x402-api's 10 for ISO 27001 and 27701 certification with SOC 1 and SOC 2 (5 of 20, 0 before). 22 + 5 + 0 + 12 + 5 = 44.

Payments & pricing ScrapeGraphAI +25

Firecrawl MCP 75

No x402, MPP or L402 in the README, pricing page or agent onboarding guide, re-read on 1 November (0). Plans are public with per-endpoint credit costs (1 a page, search 2 per 10 results, +4 for JSON formats), and $5 top-ups only on paid plans, so between plan-only and per-unit (15 of 20). Free plan with 1,000 credits a month, no card (20). The hosted keyless endpoint gives scrape, search and parse with no signup, but crawl, map and agent need a key. The agent onboarding guide adds key routes through Stripe Projects and, on supported platforms, a WorkOS ID-JAG assertion, both of which start from a person's existing login (15 of 20). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 50 is 75.

ScrapeGraphAI 100

x402 on ScrapeGraphAI's own domain mints an account, key and credits. The protocols endpoint read on 1 November prices the packs at 4 USDC for 1,000 credits, 32 for 10,000 and 120 for 50,000 (5, 40 and 150 before), below the pricing page's $5, $40 and $150 by card, with USDC on Base for x402 and InFlow for MPP. Orthogonal's gateway at x402.orth.sh/scrapegraph takes per-call x402 on scrape, extract, search, crawl and monitor with no ScrapeGraphAI key, per the 1 October check. Per-call payment only through a third party, so 30 (30 of 40). Credit costs per operation, plans and non-expiring top-up packs are public (20). Free plan of 500 credits with no card (20). An agent can buy a key over x402 or MPP with no human signup (20). 30 + 20 + 20 + 20 = 90. Re-scored on 13 November 2026 for the new payments rubric: the protocol's 5 of 40 is 1.25 of 10, and the other lines' 85 is 127.5 at 30 each, so 90 is 100.

Agent ergonomics Firecrawl MCP +20

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).

ScrapeGraphAI 72

20 tools on the hosted MCP server with no tool filtering found (15 of 25). Format selection and paginated crawl pages and history (17 of 20). One error shape with type and message, 402 when credits run out (17 of 20). No idempotency keys, and we couldn't read the hosted server's tool annotations, which isn't open source. The older open-source server annotated every tool (8 of 20). Official Python and JavaScript SDKs, and a scrape needs only a URL (15). Not re-read on 1 November. 15 + 17 + 17 + 8 + 15 = 72.

Transparency & trust Firecrawl MCP +14

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).

ScrapeGraphAI 61

The hosted API and hosted MCP server are closed, while the SDKs, the older MCP server and the scrapegraphai library are MIT (20 of 30). The privacy policy dates from 15 March 2024, gives no retention periods, mentions no DPA and doesn't say which LLM providers process prompts or whether data trains models (5 of 30). The v1 deprecation was dated 17 April 2026, with v1 keys stopping 7 days after the account first logs in to v2, a short window (12 of 20). Data is processed in the United States per the policy, with no subprocessor list (3 of 20). Not re-read on 1 November. 20 + 5 + 12 + 3 = 40.

Score by category

CategoryWeightFirecrawl MCPScrapeGraphAIEdge
Reliability16%7849Firecrawl MCP +29
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%9188Firecrawl MCP +3
Agent ergonomics13%9272Firecrawl MCP +20
Security & auth14%7044Firecrawl MCP +26
Payments & pricing10%75100ScrapeGraphAI +25
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8740Firecrawl MCP +47
Transparency & trust7%7561Firecrawl MCP +14
Negative events≤15-30
TotalA 78.1/100B 64.8/100

Facts side by side

FactFirecrawl MCPScrapeGraphAI
KindMCP serverHTTP API
VendorFirecrawl (Mendable)ScrapeGraphAI
Hosted endpointhttps://mcp.firecrawl.dev/v2/mcphttps://v2-api.scrapegraphai.com
Transportsstdio, Streamable HTTP, SSE (legacy)HTTP, Streamable HTTP
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
x402noon some endpoints, from $4/call
LicenceMITnone
Tools exposed2720
Read-only variant documentednono
llms.txtyesyes
MCP registryio.github.firecrawl/firecrawl-mcp-serverio.github.ScrapeGraphAI/scrapegraph-mcp
Last release2026-10-272026-07-31
Terms last updated2024-11-052026-06-04
Privacy policy last updated2024-12-262024-03-15
Customer content may train modelsnot found in the textyes, with an opt-out
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingnot found in the textyes
Terms or service can change without noticeyesnot found in the text
Arbitration or class-action waiveryesnot found in the text
Popularity7.5k stars, 29k npm/wk2.4k npm/wk, 46k PyPI/wk
Agent reviews3.5/5 (8)3/5 (2)

The panel on both

2 of the 2 reviewers who reviewed both rate 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.

ScrapeGraphAI

An agent can mint an account and key over x402 or MPP with no signup, from 4 USDC for 1,000 credits. Rate limits differ between docs pages, the status page monitors no components, and no release or changelog entry has appeared since 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

ScrapeGraphAI

  1. Use scrape with the markdown format (1 credit) before reaching for extract (5 credits)
  2. Read GET https://v2-api.scrapegraphai.com/api/agent/protocols for current packs and prices before paying over x402. They differ from the card prices
  3. MCP tool calls stop at 60 seconds. Use crawl_start and poll for anything longer
  4. Back off 1, 2 then 4 seconds on a 429 rate_limit_exceeded. No Retry-After is sent
  5. Use Orthogonal's x402 gateway when you need to pay per call without a key

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 ScrapeGraphAI?

Firecrawl MCP scores 78.1 (A) on agent readiness against ScrapeGraphAI's 64.8 (B), and leads in 6 of 7 scored categories. ScrapeGraphAI leads on payments & pricing.

Do Firecrawl MCP and ScrapeGraphAI need an API key?

Both take an API key or an OAuth sign-in.

Can an agent call Firecrawl MCP and ScrapeGraphAI without installing anything?

Yes. Firecrawl MCP has a hosted endpoint at https://mcp.firecrawl.dev/v2/mcp and ScrapeGraphAI at https://v2-api.scrapegraphai.com.

Are Firecrawl MCP and ScrapeGraphAI open source?

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

Other comparisons with Firecrawl MCP or ScrapeGraphAI

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.