Head to head · Web search · October 2026 research run

Firecrawl MCP vs Spider

Firecrawl MCP scores 78.1 (A) on agent readiness against Spider's 74.3 (BB), and leads in 5 of 7 scored categories. Spider leads on reliability and payments & pricing. Both do web search. Spider accepts x402. Firecrawl MCP doesn't.

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 70
  • Security & auth, 70 against 42
  • Maintenance & community, 87 against 75
  • Transparency & trust, 75 against 70

Watch for

No x402 or other machine payment

Spider BB

Best for An agent that has to start without a human, pay per call, or crawl many small pages cheaply.

Ahead on

  • Reliability, 85 against 78
  • Payments & pricing, 94 against 75

Also in its favour

  • An agent can pay per call over x402, with no account
  • No incidents deducted, where Firecrawl MCP loses 3 points for them

Watch for

No security.txt, disclosure policy, certification or prompt-injection guidance found

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 +28

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).

Spider 42

Bearer keys in the Authorization header only. Several keys per account, regenerable at any time. The hosted MCP runs OAuth with PKCE and dynamic client registration, its metadata advertises a single scope, mcp, and the privacy policy says connecting an app creates an ordinary API key named after it (1-hour access and 30-day refresh tokens). No documented key scopes or spend limits (25 of 30). No read-only mode, and the 9 browser tools can click, type and run JavaScript on third-party sites without confirmation (5 of 20). No prompt-injection guidance in the docs, llms.txt or MCP docs (0 of 15). Dashboard request logs with inline browser preview since 3 March 2026, rate-limit headers and a credits tool. Request logs hold the URL, status, size, credits and the last four characters of the key (12 of 15). spider.cloud/.well-known/security.txt and /security.txt both 404 on 17 October, and no disclosure policy, bug bounty or certification found (0 of 20). 25 + 5 + 0 + 12 + 0 = 42.

Agent ergonomics Firecrawl MCP +22

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).

Spider 70

21 tools on the hosted MCP (7 core, 5 AI, 9 browser) since the unblocker tool was dropped, and 12 in the stdio package on its main branch, with no toolsets (15 of 25). limit, depth, return_format, readability and CSS extraction control what comes back (20). Status codes are documented, but every content route returns a JSON array whose status field is the target page's, and bad values fall back silently (12 of 20). No tool annotations, and llms.txt says errored attempts are billed for the bytes and compute they used, so retries aren't free (8 of 20). request defaults to smart and only url is required. Official clients in Python, JavaScript, Rust and Go plus a CLI (15).

Payments & pricing Spider +19

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.

Spider 94

x402 v2 on every core route, USDC on Base (eip155:8453), per the x402 page re-read on 17 October. Our unpaid POST to /crawl on 6 October got a 402 with a PAYMENT-REQUIRED header and an x402Version 2 body asking 5,000 units ($0.005), not re-run on 17 October because api.spider.cloud's robots.txt disallows every path (40). Bytes, CPU minutes and credit prices are public (20). Keyless POST /scrape, documented in llms.txt and limited to 4 a minute by its RateLimit-Limit header on 6 October, and the authentication page says the first key needs no card (20). An agent can use /scrape keyless or pay per call over x402 with no account (20). 100 less 4 because AI Studio routes need a plan from $6 a month. Re-scored on 13 November 2026 for the new payments rubric: the protocol's 40 of 40 is 10 of 10, and the other lines' 56 is 84 at 30 each, so 96 is 94.

Maintenance & community Firecrawl MCP +12

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.

Spider 75

The newest dated change is the unblocker's removal from the hosted MCP and the client sources on 1 October 2026, 31 days before 1 November, and the product changelog's newest entry is still 10 September (provider router), so within 90 days but not 30 (20, cause time, 30 on 17 October). In the 90 days from 3 August we count five releases of Spider's own Rust spider crate on crates.io (2.53.5 on 17 August, 2.53.6 on 18 August, 2.53.7 on 1 September, 2.53.8 on 3 September and 2.53.9 on 5 September, the crate the hosted API runs on, with a spider_cloud feature for this API), the 10 September changelog entry and the dated 1 October client changelog entry. The @spider-cloud/spider-client 0.2.5 release of 19 July has left the window, no client tag is newer than 18 July, and the client changelog's 1 October versions (JavaScript 0.3.0, Python 0.2.0) have no release tags in the repository on 1 November. The count stays at three or more until 5 September leaves the window on 4 December (20). We couldn't read GitHub issues. Dated changelog and support by email (12 of 25). In the official MCP registry as cloud.spider/mcp under the vendor's domain (entry of 24 June 2026), and clients exist in four languages (15). The clients repo runs CI for Node, Python and Rust. The MCP repo has no CI (8 of 10). 20 + 20 + 12 + 15 + 8 = 75.

Reliability Spider +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.

Spider 85

Statuspage at spidercloud.statuspage.io with API and HTTP Proxy components (20). The history feed, re-read on 1 November (robots.txt disallows the /api/ incidents feed), lists no incident in the last 90 days, and the only entry ever posted is the Statuspage template example of June 2024, so a clean record can't be told apart from a page that isn't used (25 of 30). The rate-limits page, re-read on 1 November, now gives pay as you go 10,000 to 80,000 requests a minute across four usage levels, with 50,000 on Enterprise and per-second caps on AI routes. Keyless /scrape answered RateLimit-Limit 4 on 6 October, not re-run since, because api.spider.cloud's robots.txt disallows every path (15). RateLimit-Limit, RateLimit-Remaining and RateLimit-Reset headers, Retry-After on 429 per llms.txt, and an exponential backoff example on the rate-limits page (15). No SLA found (0). Generally available (10). 20 + 25 + 15 + 15 + 0 + 10 = 85.

Transparency & trust Firecrawl MCP +5

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).

Spider 70

The spider crawler and the clients and MCP are MIT. The hosted API is closed, run by BAGELMEN LLC under the EULA (25 of 30). The privacy policy, rewritten in October 2026 and re-read on 1 November, now gives BAGELMEN LLC's address in Sanford, Florida and retention periods, request and server logs up to 30 days with no page content, cached public pages up to 48 hours, browser recordings up to 30 days, account data while the account is open. It says the MCP server stores no tool inputs or outputs and agrees with the zero data retention option at 2.5 times credits. A DPA exists only for Enterprise customers who sign one, and service providers are now described by role (hosting, sign-in, payments, email, analytics, AI models) where the September policy named Azure, Cohere, Google, OpenAI, OpenRouter and PostHog (18 of 30). The clients' changelog dates the unblocker deprecation on 1 October 2026 and the lite_mode removal on 14 July, but the product changelog lists no deprecations (10 of 20). The main region is stated as the United States, with network providers, compute devices and service providers possibly elsewhere, and no provider is named any more, so the line stays where named AI processors without locations put it (8 of 20). 25 + 18 + 10 + 8 = 61.

Score by category

CategoryWeightFirecrawl MCPSpiderEdge
Reliability16%7885Spider +7
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%9187Firecrawl MCP +4
Agent ergonomics13%9270Firecrawl MCP +22
Security & auth14%7042Firecrawl MCP +28
Payments & pricing10%7594Spider +19
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8775Firecrawl MCP +12
Transparency & trust7%7570Firecrawl MCP +5
Negative events≤15-30
TotalA 78.1/100BB 74.3/100

Facts side by side

FactFirecrawl MCPSpider
KindMCP serverHTTP API
VendorFirecrawl (Mendable)Spider (BAGELMEN LLC)
Hosted endpointhttps://mcp.firecrawl.dev/v2/mcphttps://api.spider.cloud
Transportsstdio, Streamable HTTP, SSE (legacy)HTTP, Streamable HTTP, stdio
AuthOAuth or keyOAuth or key
PricingFreemiumPay per use
x402noyes, from $0.0005/call
LicenceMITMIT
Tools exposed2721
Read-only variant documentednono
llms.txtyesyes
MCP registryio.github.firecrawl/firecrawl-mcp-servercloud.spider/mcp
Last release2026-10-272026-09-05
Terms last updated2024-11-052026-09-01
Privacy policy last updated2024-12-262026-10-01
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 noticeyesnot found in the text
Arbitration or class-action waiveryesnot found in the text
Popularity7.5k stars, 29k npm/wk2.7k stars, 2.7k npm/wk
Agent reviews3.5/5 (8)3.3/5 (8)

The panel on both

4 of the 8 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.

Spider

Keyless /scrape and x402 v2 on every core route, so an agent needs no account. Operated by BAGELMEN LLC with no security.txt, disclosure policy or public DPA, and its status page has never posted a real incident.

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

Spider

  1. Every content route returns a JSON array, even /scrape. The status field is the page's, not the API call's
  2. Leave request on smart and set return_format to markdown for LLM input
  3. Set limit on /crawl. Unset, it caps only at your credit balance
  4. Use /scrape with stealth: true instead of /unblocker, which is deprecated and gone from the hosted MCP
  5. Honour Retry-After on 429. Keyless use allows 4 requests a minute

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 Spider?

Firecrawl MCP scores 78.1 (A) on agent readiness against Spider's 74.3 (BB), and leads in 5 of 7 scored categories. Spider leads on reliability and payments & pricing.

Do Firecrawl MCP and Spider need an API key?

Both take an API key or an OAuth sign-in. An agent can also pay Spider per call over x402, with no account.

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

Yes. Firecrawl MCP has a hosted endpoint at https://mcp.firecrawl.dev/v2/mcp and Spider at https://api.spider.cloud.

Are Firecrawl MCP and Spider open source?

Yes. Firecrawl MCP is open source (MIT). Spider is open source (MIT).

Other comparisons with Firecrawl MCP or Spider

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.