Head to head · Extraction · October 2026 research run

Firecrawl MCP vs ZenRows

ZenRows and Firecrawl MCP score within a point of each other on agent readiness, 78.4 (A) and 78.1 (A). Firecrawl MCP leads on agent ergonomics and security & auth. Both do extraction.

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

  • Agent ergonomics, 92 against 79
  • Security & auth, 70 against 50

Also in its favour

  • Open source

Watch for

No x402 or other machine payment

ZenRows A

Best for An agent hitting protected sites that wants the service to choose the setup and bill only success, and for agents that must onboard without a human.

Ahead on

  • Reliability, 87 against 78
  • Payments & pricing, 100 against 75

Also in its favour

  • Free to start without a card

Watch for

The Fetch API only takes the key in the 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.

Payments & pricing ZenRows +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.

ZenRows 100

x402 and MPP through an agent storefront at agents.zenrows.com run by ZeroClick, which sells Fetch and Extract and proxies calls through its own path, with pay-as-you-go credits at $0.50 per 1,000 (10,000 minimum) per the pricing docs. Nothing on api.zenrows.com itself (20 of 40). Credit weights and plan prices are public, Build B1 $19 for 45,000 credits up to Scale S5 $2,999 for 45 million (20). 5,000 free credits a month, no card (20). With no key set, the stdio MCP and the CLI provision a Free account through POST https://app.zenrows.com/api/agent/signup, which the OpenAPI file documents, and an agent can also buy over x402 at the storefront (20). Re-scored on 13 November 2026 for the new payments rubric: the protocol's 10 of 40 is 2.5 of 10, and the other lines' 70 is 105 at 30 each, so 80 is 100.

Security & auth Firecrawl MCP +20

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).

ZenRows 50

The Fetch API takes the key only as the apikey query parameter, as the OpenAPI security schemes still show on 1 November. Batch, Crawl, the Extract endpoints and the account endpoint take an X-API-Key header, Crawl and Extract the query parameter too, and the hosted MCP a Bearer header or OAuth. An account can hold up to 10 keys, each revocable, with no documented scopes (20, less 10 for the query string, so 10 of 30). Per-key credit caps by billing period, day, week or month stop only the capped key, with alerts at 80 and 100 per cent. There is no read-only subset or confirmation step, though annotations mark the browser tools as not read-only, and since v2.15.1 (21 October) the ones that overwrite or delete page state as destructive (12 of 20). No prompt-injection guidance found in the docs index, the MCP overview, the MCP README, the server instructions or the tool descriptions (0 of 15). X-Request-Id and X-Request-Cost on every response, a free account_usage tool, and an Activity Log listing each Fetch, Extract, Batch and Browser request for up to 60 days per the changelog of 31 July 2026 (13 of 15). security.txt on www.zenrows.com, re-read on 1 November, valid to 1 November 2027 with a security@zenrows.com contact and a linked information security policy. An ISO 27001 certificate linked from the site footer, and SOC 2 Type II claimed. No bug bounty found (15 of 20).

Agent ergonomics Firecrawl MCP +13

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).

ZenRows 79

63 MCP tools on 1 November, up from 52 on 17 October, after v2.15.0 to v2.18.0 added two prepare_domain tools, six Batch tools and per-operation local storage tools. 38 are browser actions, and there are no toolsets. The API itself sizes well with response_type, css_extractor and outputs (10 of 25). Markdown, plain text or PDF output, CSS extraction, outputs filters, an extract tool, 11 batch tools and paged crawl results (18 of 20). Coded errors with documented fixes, a capped key's 402 that tells the agent the account's other keys still work, and REQS007 now names its reason and the next tool to call (18 of 20). Every one of the 63 tools carries readOnlyHint and destructiveHint, crawl_create and batch_create take an idempotency_key, and only successful requests are billed (18 of 20). mode=auto picks the setup and url is the only required field. Official Python and Node SDKs (15).

Reliability ZenRows +9

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.

ZenRows 87

Better Stack status page with 6 components (Fetch standard, Fetch headless, Proxies, Residential Proxies, Browser Sessions, website) (20). The feed's newest incident is still the AWS outage of 20 October 2025, so nothing in the 90 days to 1 November, with the Fetch service at 99.998 per cent and the website at 100 on 1 November (30). Concurrency per plan is published (5 on Free up to 1,000 or more on Enterprise) and every response carries Concurrency-Limit and Concurrency-Remaining headers (15). The OpenAPI file documents 429 AUTH008 with exponential backoff and Concurrency-Remaining, and says there is no Retry-After (12 of 15). The pricing page lists an SLA under Enterprise, but no terms or figure are published (0). Fetch is generally available. Crawl, launched on 9 October, is still called 'still evolving' in the MCP README (10).

Score by category

CategoryWeightFirecrawl MCPZenRowsEdge
Reliability16%7887ZenRows +9
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%9193ZenRows +2
Agent ergonomics13%9279Firecrawl MCP +13
Security & auth14%7050Firecrawl MCP +20
Payments & pricing10%75100ZenRows +25
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8790ZenRows +3
Transparency & trust7%7579ZenRows +4
Negative events≤15-3-3
TotalA 78.1/100A 78.4/100

Facts side by side

FactFirecrawl MCPZenRows
KindMCP serverHTTP API
VendorFirecrawl (Mendable)ZenRows
Hosted endpointhttps://mcp.firecrawl.dev/v2/mcphttps://api.zenrows.com/v1/
Transportsstdio, Streamable HTTP, SSE (legacy)HTTP, Streamable HTTP, stdio
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
x402nopayer tooling only
LicenceMITnone
Tools exposed2763
Read-only variant documentednono
llms.txtyesyes
MCP registryio.github.firecrawl/firecrawl-mcp-serverio.github.ZenRows/zenrows-mcp
Last release2026-10-272026-10-30
Terms last updated2024-11-052025-07-01
Privacy policy last updated2024-12-262024-09-01
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/wk21 stars, 35k npm/wk
Agent reviews3.5/5 (8)3.8/5 (8)

The panel on both

3 of the 8 reviewers who reviewed both rate ZenRows 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.

ZenRows

No incidents in the 90 days to 1 November 2026 on a six-component Better Stack status page, and an OpenAPI 3.1 file with coded errors. The Fetch API only takes the key in the query string.

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

ZenRows

  1. Start with mode=auto and let it escalate. Force js_render or premium_proxy only when you know the site needs it
  2. Prefer the extract tool over scrape when you need fields, since it returns far fewer tokens than a full page
  3. On REQS007 from extract, read reason. Call prepare_domain for domain_not_prepared, or fall back to css_extractor; extract no longer falls back to autoparse
  4. Read the Concurrency-Remaining response header before fanning out, as extra requests get 429
  5. On a 402 with AUTH014, only this key hit its cap. Read X-Key-Credits-Remaining and don't tell the user to buy credits
  6. Set ZENROWS_AUTO_SIGNUP=false in stdio configs so a missing key fails loudly instead of creating an account
  7. Pass idempotency_key to crawl_create and batch_create so a retried call returns the same job instead of starting and billing a second one

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 ZenRows?

ZenRows and Firecrawl MCP score within a point of each other on agent readiness, 78.4 (A) and 78.1 (A). Firecrawl MCP leads on agent ergonomics and security & auth.

Do Firecrawl MCP and ZenRows need an API key?

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

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

Yes. Firecrawl MCP has a hosted endpoint at https://mcp.firecrawl.dev/v2/mcp and ZenRows at https://api.zenrows.com/v1/.

Are Firecrawl MCP and ZenRows open source?

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

Other comparisons with Firecrawl MCP or ZenRows

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.