Head to head · Web search · October 2026 research run

Firecrawl MCP vs Scrapingdog

Firecrawl MCP scores 78.1 (A) on agent readiness against Scrapingdog's 40.3 (E), and leads in every scored category. 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
  • Schema & documentation, 91 against 53
  • Agent ergonomics, 92 against 52
  • Security & auth, 70 against 5
  • Payments & pricing, 75 against 60
  • Maintenance & community, 87 against 25
  • Transparency & trust, 75 against 56

Also in its favour

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

Watch for

No x402 or other machine payment

Scrapingdog E

Best for A budget agent that wants parsed Google, Amazon or LinkedIn results and can keep the key out of logs.

Also in its favour

  • Free to start without a card

Watch for

The REST API takes the key only in the URL query string

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.

Security & auth Firecrawl MCP +65

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).

Scrapingdog 5

One account key with no scopes, and we found no rotation or revocation docs; team members get their own keys (10). The REST API takes the key only in the api_key query string, with no header option, so less 10 (0 of 30). The hosted MCP server takes the key as a bearer header, then passes it to the API in the query string. No read-only mode or least-privilege key. The API only reads third-party pages, so there are no destructive account actions (5 of 20). No prompt-injection guidance in the docs, the onboarding guide or the MCP README (0 of 15). No request log or per-call audit found; /account reports credits and concurrency only (0 of 15). No security.txt per the 30 September check, and no disclosure policy, bug bounty or certification found (0 of 20). Total 5.

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.

Scrapingdog 25

The newest dated releases are the SDKs and MCP server first published on 31 July and 1 August 2026, 102 days ago; no API changelog or later dated release found. The MCP repository became a hosted service at mcp.scrapingdog.com in commits of 25 and 26 October with no version bump, tag or changelog entry, so not a release (10 of 30). Nothing dated in the 90 days from 12 August (0 of 20). We couldn't read GitHub issues. The MCP repository has 13 commits, the last seven on 25 and 26 October, and support is by chat and email (5 of 25). Node and Python SDKs, current per the 1 October check; npm and PyPI weren't readable on 10 November (8 of 15). The MCP repository now runs typecheck, build and a smoke suite in CI before each deploy, with no tags or readable run results (2 of 10, the earlier partial held). Total 25.

Agent ergonomics Firecrawl MCP +40

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).

Scrapingdog 52

35 MCP tools with no toolsets or subsets (5 of 25). markdown=true, ai_query and parsed JSON endpoints for Google, Amazon and LinkedIn keep responses smaller. No documented pagination or size limits on the raw scrape (12 of 20). The docs list 8 status codes with meanings, and the agent onboarding guide gives each one an action (fix parameters on 400, check the key with /account on 401, a human upgrades on 403, lower concurrency and back off on 429, retry 410 once), with whether it's charged; the MCP passes the status and body back (20 of 20). Failed requests aren't billed, but no tool annotations or idempotency guidance (5 of 20). Only url is required, but rendering defaults on at 5 credits and the MCP describes it as off. Node and Python SDKs (10 of 15). Total 52.

Schema & documentation Firecrawl MCP +38

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).

Scrapingdog 53

No OpenAPI spec found. The MCP builds typed zod inputs for 35 tools from a declarative registry, and ai_extract_rules is a JSON string (12 of 25). llms.txt at the site root, re-read on 10 November, links the docs and a Markdown onboarding guide for agents (10). MCP descriptions say what each endpoint does but not when to avoid it, and the web_scrape tool tells the model the API default for dynamic is false while the docs say rendering is on by default (10 of 20). Booleans, numbers and strings with few enums, plus the JSON-string field (9 of 15). Code examples on each docs page and 8 documented status codes (12 of 15). No changelog and no versioned API paths found (0). Total 53; the score published on 1 October was 43, ten below these lines, and is corrected to their sum.

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.

Scrapingdog 49

The footer still links an UptimeRobot status page. Its monitors load only from UptimeRobot's /api/ path, which robots.txt disallows, and the page itself shows "Loading..." and a fetch error, so no component could be read (0 of 20). No readable incident history (5). Concurrency per plan is published, 1 on Free up to 2,200 on the top plan, and over the limit returns 429 (15). The agent onboarding guide linked from llms.txt says to retry 410, 429 and occasional 400s with backoff, not to retry 401 or 403, and that failed requests aren't charged; requests time out after 60 seconds. No Retry-After or idempotency keys (12 of 15). A public SLA page says Scrapingdog aims for 99 per cent monthly uptime and compensates downtime in credits, with no measurement method or date, per the 1 October check, not re-read on 10 November (7 of 10, the earlier partial held). Generally available (10). Total 49.

Transparency & trust Firecrawl MCP +19

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).

Scrapingdog 56

Closed service with terms revised 13 January 2026 (re-read 10 November), naming OpenData Labs Private Limited under the laws of Rajasthan, India, with no postal address. The MCP is MIT (15 of 30). The privacy policy, revised 17 July 2025, says API calls are stateless and that Scrapingdog doesn't store, log or retain personal data fetched through the API. A DPA is published. No retention periods for account data, per the 1 October check, not re-read on 10 November (22 of 30). No deprecation policy or dated notices found (0). No processors or data locations named (0 of 20). Total 37.

Score by category

CategoryWeightFirecrawl MCPScrapingdogEdge
Reliability16%7849Firecrawl MCP +29
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%9153Firecrawl MCP +38
Agent ergonomics13%9252Firecrawl MCP +40
Security & auth14%705Firecrawl MCP +65
Payments & pricing10%7560Firecrawl MCP +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8725Firecrawl MCP +62
Transparency & trust7%7556Firecrawl MCP +19
Negative events≤15-3-2
TotalA 78.1/100E 40.3/100

Facts side by side

FactFirecrawl MCPScrapingdog
KindMCP serverHTTP API
VendorFirecrawl (Mendable)Scrapingdog (OpenData Labs)
Hosted endpointhttps://mcp.firecrawl.dev/v2/mcphttps://api.scrapingdog.com/scrape
Transportsstdio, Streamable HTTP, SSE (legacy)HTTP, Streamable HTTP, stdio
AuthOAuth or keyAPI key
PricingFreemiumFreemium
x402nono
LicenceMITnone
Tools exposed2735
Read-only variant documentednono
llms.txtyesyes
MCP registryio.github.firecrawl/firecrawl-mcp-serverio.github.Darshan972/scrapingdog-mcp
Last release2026-10-272026-07-31
Terms last updated2024-11-052026-01-13
Privacy policy last updated2024-12-262025-07-17
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
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/wk0 stars
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.

Scrapingdog

A plain request is 1 credit, about $0.20 per 1,000 on Lite, and failed requests aren't charged. The REST API takes its key only in the URL query string, and the MCP server describes JavaScript rendering as off by default when the API turns it on at 5 credits.

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

Scrapingdog

  1. Add dynamic=false unless the page needs JavaScript. It cuts the cost from 5 credits to 1, whatever the MCP description says
  2. Connect the hosted MCP with the key as a bearer header, and keep REST request URLs out of logs, since they carry api_key
  3. Set client timeouts above 60 seconds and retry 410 and 429 with backoff. Failures aren't billed
  4. Prefer the parsed endpoints (Google, Amazon) over scraping the raw page when one exists

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 Scrapingdog?

Firecrawl MCP scores 78.1 (A) on agent readiness against Scrapingdog's 40.3 (E), and leads in every scored category.

Do Firecrawl MCP and Scrapingdog need an API key?

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

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

Yes. Firecrawl MCP has a hosted endpoint at https://mcp.firecrawl.dev/v2/mcp and Scrapingdog at https://api.scrapingdog.com/scrape.

Are Firecrawl MCP and Scrapingdog open source?

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

Other comparisons with Firecrawl MCP or Scrapingdog

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.