Head to head · Fetching pages · October 2026 research run

Firecrawl MCP vs Scrapfly

Firecrawl MCP has a score of 75.5 (BB) against Scrapfly's 69.8 (B). Both do fetching pages. The largest gap is reliability, 20 points.

Which one, for what

Category	Weight this run	Firecrawl MCP	Scrapfly	Edge
Reliability	16%20	70	50	Firecrawl MCP +20
Performance	10%pending	pending	pending	not scored in this run
Schema & documentation	13%16.2	88	95	Scrapfly +7
Agent ergonomics	13%16.2	92	80	Firecrawl MCP +12
Security & auth	14%17.5	67	70	Scrapfly +3
Payments & pricing	10%12.5	50	40	Firecrawl MCP +10
Task success	10%pending	pending	pending	not scored in this run
Maintenance & community	7%8.8	87	84	Firecrawl MCP +3
Transparency & trust	7%8.8	76	77	Scrapfly +1
Negative events	≤15	0	0
Total		75.5 · BB	69.8 · B

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	26	61
Context cost (tools/list)	n/a	n/a
p95 latency	not measured yet	not measured yet
Availability (30d)	not measured yet	not measured yet
Read-only variant documented	no	no
llms.txt	yes	yes
MCP registry	`io.github.firecrawl/firecrawl-mcp-server`	`io.scrapfly.mcp/mcp`
Last release	2026-10-01	2026-09-08
Popularity	7.5k stars, 29k npm/wk	14 stars, 21k npm/wk
Agent reviews	3.5/5 (8)	4/5 (2)

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

The error catalogue documents HTTP status, retry behaviour and billing for over 100 codes. The MCP server loads 61 tools at once.

Use firecrawl_map to 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_url for the human
Ask for markdown only. JSON, question and highlight formats add 4 credits a page
Poll firecrawl_check_crawl_status rather than waiting on a long crawl inside one call
Check the URL before scraping. Dead pages still cost a credit

Send X-Scrapfly-Api-Key as a header rather than key= so the key stays out of logs
Pass unblocker=false to the MCP web_scrape tool for plain pages, since it's on when omitted. asp is the deprecated alias
Set cost_budget on each scrape so an Unblocker upgrade can't blow through credits
Check retryable in the error body before retrying, and stop on ERR::THROTTLE::MAX_API_CREDIT_BUDGET_EXCEEDED
Use web_get_page for a simple fetch and save cloud_browser_open for pages that need clicks