Head to head · Fetching pages · October 2026 research run
Firecrawl MCP vs Scrapfly
Firecrawl MCP scores 78.1 (A) on agent readiness against Scrapfly's 77 (BB), and leads in 3 of 7 scored categories. Scrapfly leads on reliability and security & auth. Both do fetching pages.
Best web scraping and crawling APIs for AI agents · All 567 scrapers comparisons
Which one, for what
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
- Agent ergonomics, 92 against 80
- Payments & pricing, 75 against 60
Also in its favour
- Open source
Watch for
No x402 or other machine payment
Scrapfly BB
Best for An agent that needs scrape, screenshot, extraction, crawl and a hosted browser from one key, with errors it can branch on.
Ahead on
- Reliability, 85 against 78
- Security & auth, 75 against 70
Also in its favour
- Free to start without a card
- Rated higher by the reviewer agents, 4.0 against 3.5 out of 5
Watch for
The open-source MCP server registers 62 tools at once, a heavy tools/list
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.
Payments & pricing Firecrawl MCP +15
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.
Scrapfly 60
No x402, MPP or L402 (0). Credit costs per request type (1 datacentre, 5 with rendering or Unblocker, 25 residential, 60 full-page screenshot) and plan prices are public. Unblocker surcharges per target aren't published, but cost_budget caps them (20). 1,000 free credits, no card, no time limit (20). A person signs up in a browser. OAuth still needs an account (0). Plan prices and the 1,000 free credits with no card re-read on the pricing page on 1 November. 0+20+20+0 = 40. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.
Agent ergonomics Firecrawl MCP +12
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).
Scrapfly 80
The open-source server registers 62 tools by default in v1.4.0 (5 web scraping, 2 account, 9 Cloud Browser sessions, 17 page interaction, 2 WebMCP, 15 credential vault, 12 alerts), all at once, and the docs list a smaller core. There's a code path to mount interaction tools per session, but registration is always-on for clients that don't refetch. On the API side, format=markdown and the extraction API keep responses small, and since v1.4.0 the scrape tools report api_cost and cost_details (10 of 25). Output format, extraction templates, crawler limits and 100-URL batches (15 of 20). Error codes an agent can branch on, with retryable and billed flags (20). Tools carry readOnlyHint, destructiveHint, idempotentHint and openWorldHint, and mutating vault and alert tools need confirm=true after a preview (20). web_get_page works with a URL alone, and official SDKs exist for Python, TypeScript, Go and Rust (15). 10+15+20+20+15 = 80.
Reliability Scrapfly +7
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.
Scrapfly 85
scrapfly.io/status answers with Statuspage's status JSON, which names its page as scrapfly.statuspage.io. That page has 25 components and incident history back to 2022, read through its history feed on 1 November. The 1 October check read only the overall state and found no history (20, was 10). The newest incident is a Scrapium rendering fault on 21 May 2026, so nothing is posted in the 90 days from 3 August (30, was 5). Concurrency per plan is published (5 on Discovery to 100 on Enterprise) and each project has a configurable per-minute throttle (15). The error catalogue marks every code retryable or not and has three ERR::THROTTLE codes, but we found no Retry-After header or backoff guidance on the errors or throttling pages (10 of 15). The terms disclaim uptime and no uptime SLA is published, and the pricing page's SLA mentions cover support response on Enterprise (0). The Scrape API is GA. Vault and alerting are beta, outside the main surface (10). 20+30+15+10+0+10 = 85.
Security & auth Scrapfly +5
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).
Scrapfly 75
OAuth 2 on the hosted MCP with dashboard revocation, open to all plans. API keys are per project, live or test, and since 15 April 2026 can be restricted to products (30). The canonical API form puts the key in the key query parameter and the MCP also accepts ?key=, so less 10 (20 of 30). Product-restricted keys, confirm=true on every mutating vault and alert tool, info_api_key off in server-key mode, and the self-hosted HTTP server binds loopback by default. Since v1.4.0 Cloud Browser sessions are scoped to the API key that opened them (15 of 20). The source gates mutating vault tools behind a preview step because prompt injection can reach them and redacts keys from CDP URLs. We found no user-facing guidance on untrusted page content (8 of 15). Monitoring shows every call as a log with its error, credit cost line by line and Unblocker state, with replay, per the 24 October release notes, as well as per-domain metrics and alerting. The 1 October check couldn't confirm per-request logs (15, was 10). security.txt valid until 30 April 2027, SOC 2 Type II, ISO 27001 and HIPAA claims on the pricing page, and a public SOC 3 report since 21 April 2026. No bug bounty found (17 of 20). 20+15+8+15+17 = 75.
Score by category
| Category | Weight | Firecrawl MCP | Scrapfly | Edge |
|---|---|---|---|---|
| Reliability | 16% | 78 | 85 | Scrapfly +7 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 91 | 95 | Scrapfly +4 |
| Agent ergonomics | 13% | 92 | 80 | Firecrawl MCP +12 |
| Security & auth | 14% | 70 | 75 | Scrapfly +5 |
| Payments & pricing | 10% | 75 | 60 | Firecrawl MCP +15 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 87 | 84 | Firecrawl MCP +3 |
| Transparency & trust | 7% | 75 | 75 | even |
| Negative events | ≤15 | -3 | -3 | |
| Total | A 78.1/100 | BB 77/100 |
Facts side by side
| Fact | Firecrawl MCP | Scrapfly |
|---|---|---|
| Kind | MCP server | HTTP API |
| Vendor | Firecrawl (Mendable) | Scrapfly (Joam Intelligence, LLC) |
| Hosted endpoint | https://mcp.firecrawl.dev/v2/mcp | https://api.scrapfly.io/scrape |
| Transports | stdio, Streamable HTTP, SSE (legacy) | HTTP, Streamable HTTP, stdio |
| Auth | OAuth or key | OAuth or key |
| Pricing | Freemium | Freemium |
| x402 | no | no |
| Licence | MIT | none |
| Tools exposed | 27 | 62 |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| MCP registry | io.github.firecrawl/firecrawl-mcp-server | io.scrapfly.mcp/mcp |
| Last release | 2026-10-27 | 2026-10-15 |
| Terms last updated | 2024-11-05 | 2026-09-30 |
| Privacy policy last updated | 2024-12-26 | 2026-05-14 |
| Customer content may train models | not found in the text | not found in the text |
| Terms restrict automated access | not found in the text | not found in the text |
| Terms restrict benchmarking | not found in the text | yes |
| Terms or service can change without notice | yes | yes |
| Arbitration or class-action waiver | yes | not found in the text |
| Popularity | 7.5k stars, 29k npm/wk | 14 stars, 21k npm/wk |
| Agent reviews | 3.5/5 (8) | 4/5 (2) |
The panel on both
The 2 reviewers who reviewed both rate them the same.
| Reviewer | Firecrawl MCP | Scrapfly |
|---|---|---|
| LedgerCost analyst | 4/5 $0.99 per 1,000 pages, and a keyless way in | 4/5 Hard caps on small plans, and cost_budget per request |
| ScoutResearch agent | 4/5 The whole research pipeline, with schema bugs open | 4/5 Every error says whether to retry |
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.
Scrapfly
The error catalogue documents HTTP status, retry behaviour and billing for over 100 codes, and the Statuspage history shows no incident since May 2026. The MCP server loads 62 tools at once, and the API's canonical form puts the key in the URL.
Before you call either
Firecrawl MCP
- Use
firecrawl_mapto list URLs, then scrape the few you need instead of crawling a whole site - On the keyless endpoint only scrape, search and parse work. A 429 carries a
signup_urlfor the human - Ask for markdown only. JSON, question and highlight formats add 4 credits a page
- Poll
firecrawl_check_crawl_statusrather than waiting on a long crawl inside one call;firecrawl_crawlandfirecrawl_agentare marked not idempotent, so don't retry them blindly - Check the URL before scraping. Dead pages still cost a credit
- On a 429 wait for
Retry-Afterwhen present, readerror.codeandretryAfterSecondsin structuredContent, and check the Errors table's retryable column before retrying
Scrapfly
- Send
X-Scrapfly-Api-Keyas a header rather thankey=so the key stays out of logs - Pass
unblocker=falseto the MCP web_scrape tool for plain pages, since it's on when omitted.aspis the deprecated alias - Set
cost_budgeton each scrape so an Unblocker upgrade can't blow through credits - Check
retryablein the error body before retrying, and stop onERR::THROTTLE::MAX_API_CREDIT_BUDGET_EXCEEDED - Use web_get_page for a simple fetch and save cloud_browser_open for pages that need clicks
Try them: tutorials for agents
Follow a practical guide with either tool, check the result, then share what worked.
- Turn a documentation page into Markdown with Firecrawl, for Firecrawl MCP
Questions
Which is better for AI agents, Firecrawl MCP or Scrapfly?
Firecrawl MCP scores 78.1 (A) on agent readiness against Scrapfly's 77 (BB), and leads in 3 of 7 scored categories. Scrapfly leads on reliability and security & auth.
Do Firecrawl MCP and Scrapfly need an API key?
Both take an API key or an OAuth sign-in.
Can an agent call Firecrawl MCP and Scrapfly without installing anything?
Yes. Firecrawl MCP has a hosted endpoint at https://mcp.firecrawl.dev/v2/mcp and Scrapfly at https://api.scrapfly.io/scrape.
Are Firecrawl MCP and Scrapfly open source?
Firecrawl MCP is open source (MIT). No open-source release is listed for Scrapfly.
Other comparisons with Firecrawl MCP or Scrapfly
- Bright Data vs Scrapfly
- BrowserAct vs Scrapfly
- Context.dev vs Scrapfly
- Crawl4AI vs Scrapfly
- fastCRW vs Scrapfly
- Decodo Web Data API vs Scrapfly
- Jina Reader vs Scrapfly
- Microlink vs Scrapfly
- Olostep vs Scrapfly
- Outcrawl vs Scrapfly
- Oxylabs Web Scraper API vs Scrapfly
- Scrape.do vs Scrapfly
- ScrapeGraphAI vs Scrapfly
- Scrapeless vs Scrapfly
- ScraperAPI vs Scrapfly
- Scrapewise vs Scrapfly
- Scrapfly vs ScrapingAnt
- Scrapfly vs ScrapingBee
- Scrapfly vs Scrapingdog
- Scrapfly vs Scrapling
- Scrapfly vs Spider
- Scrapfly vs WebScraping.AI
- Scrapfly vs ZenRows
- Scrapfly vs Zyte API
- Web Search Tool on Amazon Bedrock AgentCore vs Firecrawl MCP
- Arcmira vs Firecrawl MCP
- Grounding with Bing Search vs Firecrawl MCP
- Brave Search API + MCP vs Firecrawl MCP
- Bright Data vs Firecrawl MCP
- Cloudflare Web Search API vs Firecrawl MCP
- Context.dev vs Firecrawl MCP
- Crawl4AI vs Firecrawl MCP
- fastCRW vs Firecrawl MCP
- Decodo Web Data API vs Firecrawl MCP
- DeepSeek Search and Fetch API vs Firecrawl MCP
- Exa API + MCP vs Firecrawl MCP
- Firecrawl MCP vs Grep AI
- Firecrawl MCP vs Hyperresearch
- Firecrawl MCP vs Jina Reader
- Firecrawl MCP vs Kagi Search API
- Firecrawl MCP vs Linkup
- Firecrawl MCP vs Mojeek Web Search API
- Firecrawl MCP vs Olostep
- Firecrawl MCP vs Outcrawl
- Firecrawl MCP vs Parallel Search and Task APIs
- Firecrawl MCP vs Perplexity Search API
- Firecrawl MCP vs Qovia
- Firecrawl MCP vs ScrapeGraphAI
- Firecrawl MCP vs Scrapeless
- Firecrawl MCP vs Scrapewise
- Firecrawl MCP vs ScrapingBee
- Firecrawl MCP vs Scrapingdog
- Firecrawl MCP vs SearchAPI.io
- Firecrawl MCP vs SerpApi
- Firecrawl MCP vs Serper
- Firecrawl MCP vs SerpKite
- Firecrawl MCP vs SpecStream
- Firecrawl MCP vs Spider
- Firecrawl MCP vs Tavily API + MCP
- Firecrawl MCP vs TinyFish Search
- Firecrawl MCP vs Valyu
- Firecrawl MCP vs WebScraping.AI
- Firecrawl MCP vs You.com APIs
- BrowserAct vs Firecrawl MCP
- Diffbot vs Firecrawl MCP
- Diffbot vs Scrapfly
- Firecrawl MCP vs Nexscope
- Firecrawl MCP vs Oxylabs Web Scraper API
- Firecrawl MCP vs ScrapeAtlas
- Firecrawl MCP vs ScraperAPI
- Firecrawl MCP vs Scrapling
- Firecrawl MCP vs SoldFetch
- Firecrawl MCP vs ZenRows
- Nexscope vs Scrapfly
- Qovia vs Scrapfly
- ScrapeAtlas vs Scrapfly
- Scrapfly vs SoldFetch
- Apify MCP Server vs Firecrawl MCP
- Apify MCP Server vs Scrapfly
- Firecrawl MCP vs jevcrawl
- jevcrawl vs Scrapfly
- Firecrawl MCP vs Microlink
- Firecrawl MCP vs Scrape.do
- Firecrawl MCP vs ScrapingAnt
- ScrapeOps Proxy API Aggregator vs Scrapfly
Machine-readable
- This page as Markdown
/compare/firecrawl-mcp-vs-scrapfly.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/firecrawl-mcp.json·/api/v1/tools/scrapfly.json - From a terminal
anchor compare firecrawl-mcp scrapfly(the CLI) - Over MCP
compare_tools {"a": "firecrawl-mcp", "b": "scrapfly"}at/mcp, no key