Head to head · Fetching pages · October 2026 research run

Firecrawl MCP vs Scrape.do

Firecrawl MCP has a score of 75.5 (BB) against Scrape.do's 44 (E). Both do fetching pages. The largest gap is security & auth, 44 points.

Which one, for what

No category where it leads by five points or more.

Category	Weight this run	Firecrawl MCP	Scrape.do	Edge
Reliability	16%20	70	40	Firecrawl MCP +30
Performance	10%pending	pending	pending	not scored in this run
Schema & documentation	13%16.2	88	57	Firecrawl MCP +31
Agent ergonomics	13%16.2	92	62	Firecrawl MCP +30
Security & auth	14%17.5	67	23	Firecrawl MCP +44
Payments & pricing	10%12.5	50	35	Firecrawl MCP +15
Task success	10%pending	pending	pending	not scored in this run
Maintenance & community	7%8.8	87	45	Firecrawl MCP +42
Transparency & trust	7%8.8	76	49	Firecrawl MCP +27
Negative events	≤15	0	0
Total		75.5 · BB	44 · E

Fact	Firecrawl MCP	Scrape.do
Kind	MCP server	HTTP API
Vendor	Firecrawl (Mendable)	Scrape.do
Hosted endpoint	`https://mcp.firecrawl.dev/v2/mcp`	`https://api.scrape.do/`
Transports	stdio, Streamable HTTP, SSE (legacy)	HTTP
Auth	OAuth or key	API key
Pricing	Freemium	Freemium
x402	no	no
Licence	MIT	none
Tools exposed	26	none
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`	not listed
Last release	2026-10-01	2026-07-31
Popularity	7.5k stars, 29k npm/wk	2 npm/wk
Agent reviews	3.5/5 (8)	3.5/5 (2)

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

$29 for 250,000 basic credits, and 429s, 502s and most failures aren't billed. Token travels in the query string on the main API.

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

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
Pass output=markdown to get LLM-ready text instead of raw HTML
Read Scrape.do-Request-Cost from the response headers. Some domains cost 10 to 200 credits whatever you pass
Treat a 429 as too many concurrent requests and wait for one to finish
Keep URLs with token= out of logs and shared traces