Head to head · Crawling · October 2026 research run

jevcrawl vs Scrapling

Scrapling scores 68.5 (B) on agent readiness against jevcrawl's 66.1 (B), and leads in 3 of 7 scored categories. jevcrawl leads on agent ergonomics and security & auth. Both do crawling.

Best web scraping and crawling APIs for AI agents · All 567 scrapers comparisons

Which one, for what

jevcrawl B

Best for An agent that must find one answer several clicks deep on a documentation or help site and wants a few thousand tokens back instead of whole pages.

Ahead on

  • Agent ergonomics, 80 against 71
  • Security & auth, 59 against 39

Watch for

First released on 13 October 2026, version 0.2.0 and marked alpha, with one maintainer

Scrapling B

Best for Agents that need to fetch and drive pages locally, including JavaScript-heavy or bot-protected ones, without a hosted scraping bill.

Ahead on

  • Payments & pricing, 90 against 45
  • Maintenance & community, 93 against 68

Also in its favour

  • No key needed to call it

Watch for

Version 0.5.1 with a Beta classifier. v0.4.15, v0.5 and v0.5.1 each carried breaking changes, the last in a patch release

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 Scrapling +45

jevcrawl 45

No payment protocol (0). The package is free, so read with the rule for the paid option it needs, TypeSafe's Jev. Per-token price published at $0.042 per million input tokens for jev-1.13.0 and jev-1.14.0, re-read on 2 November (20). No free Jev tier found. scrape without a goal works with no key, which is a small free path (5 of 20). A person has to sign in at console.typesafe.ai, and TypeSafe describes Jev as early access. The console answered 403 to our reader. Keyless goal-less scraping earns a little (5 of 20). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.

Scrapling 90

Free, self-hosted software under BSD-3-Clause with nothing to buy, read with the self-hosted rule. No payment protocol (0), nothing to price (30), free (30), no signup or key (30). 0 + 30 + 30 + 30 = 90.

Maintenance & community Scrapling +25

jevcrawl 68

v0.2.0 on 15 October 2026, 18 days before 2 November (30). Three releases between 13 and 15 October 2026 (20). One later change, the merged audit-fixes pull request of 26 October (redirect scope, per-step time limits, a 50 MB cap on gzip sitemaps), is in no release yet. No outside issues or pull requests were found on 15 October, and GitHub's issue pages couldn't be read on 2 November (8 of 25). Not in the official MCP registry, which returned no server for jevcrawl on 2 November (0). Current dependencies, a uv.lock, CI and PyPI trusted publishing in the workflows (10). 30 + 20 + 8 + 0 + 10 = 68.

Scrapling 93

v0.5.1 tagged and released on 4 November 2026, 14 days before 18 November (30). v0.4.15 (23 August), v0.5 (17 October in the changelog, tagged 18 October) and v0.5.1 (4 November), three in the 90 days (20). The v0.5.1 notes credit about a dozen pull requests from outside contributors. Five issues and 18 pull requests were open on 18 November, and the issue template points to GitHub Discussions and a Discord (20 of 25). The official MCP registry lists io.github.D4Vinci/Scrapling as active, with versions from 0.4.1 (27 February 2026) to 0.5.1 (4 November 2026) (15). Tests and code-quality workflows, PyPI trusted publishing, and current dependencies such as Playwright 1.62. Run results unread (8 of 10). 30 + 20 + 20 + 15 + 8 = 93.

Security & auth jevcrawl +20

jevcrawl 59

Read with the API and MCP lines, since the server runs locally but sends data to a hosted API. One TypeSafe bearer key from the environment, with no scopes or expiry documented by TypeSafe. The README says the key is never written to disk or logs (20). Every tool only reads, a crawl stays on the start host, and robots.txt is followed by default. There is still no check against private, loopback or link-local addresses in the source on 2 November, so an agent can be steered to internal hosts. The unreleased 26 October change skips redirects off the crawl's hosts (12). Pages are untrusted content. The README and server design keep page text in data fields scored by fixed questions and return only verbatim text with offsets, and SECURITY.md names a change in fetch behaviour through page content as in scope. These are the author's claims, untested by us (12). Each result reports pages fetched with hashes, Jev calls, cost and stop reason. No persistent call log (7). SECURITY.md with GitHub private reporting and a one-week answer. No bounty, no advisories yet, and TypeSafe publishes no security.txt (8).

Scrapling 39

Read as local software with an optional HTTP transport. stdio needs no credential. Over HTTP the server refuses to start without a token or an explicit --no-auth, and accepts one shared bearer token with no scopes, rotated by restarting (15). Annotations let a client gate the destructive tools, and follow_redirects defaults to safe, which blocks redirects to private addresses. A direct request to localhost or a private address is not refused, and there is no read-only mode (10). Hidden elements, aria-hidden content, zero-width characters, comments and template tags are stripped by default before page text reaches the model, as documented in the MCP guide. The vendor's claim, untested by us (10). Browser sessions record network history the agent and operator can read back. No call log (4). No SECURITY.md, disclosure address or bug bounty in the repository, and GitHub's advisory page couldn't be read (0). 15 + 10 + 10 + 4 + 0 = 39.

Agent ergonomics jevcrawl +9

jevcrawl 80

Three compact tools (25). max_pages, max_seconds, return_tokens and limit bound every call, and scrape can return a whole page or only the passages for a goal. No pagination is needed (18). Expected failures come back as {error, message} with a message that says what to do, and stopped_because, degraded and needs_js_urls tell the agent why a result is thin (19). All tools read only and repeats are answered from a local cache at no cost, but there are no readOnlyHint or idempotentHint annotations (10). Only goal and start_url are required, with measured defaults. The Python library is usable but undocumented (an open issue), and there is one language (8).

Scrapling 71

17 tools, and v0.5 and v0.5.1 both shortened the descriptions. No toolsets or read-only subset (15). css_selector narrows fetch output, extraction can be Markdown, HTML, text or an ARIA snapshot with search, main_content_only is on by default, and network history is paged with a cursor and a limit of 1 to 200 (18). Failures from bad input, the browser and curl come back as tool errors with the message, which the v0.5 notes say were made clearer. No error codes an agent can branch on (12). Every tool carries annotations, read-only for fetches and lists and destructive for actions, JavaScript and state files. HTTP requests retry three times by default with a one-second wait (17). Only url is required for a fetch, with schema defaults. One language, Python, plus a CLI and Docker (9). 15 + 18 + 12 + 17 + 9 = 71.

Score by category

CategoryWeightjevcrawlScraplingEdge
Reliability16%6865jevcrawl +3
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8181even
Agent ergonomics13%8071jevcrawl +9
Security & auth14%5939jevcrawl +20
Payments & pricing10%4590Scrapling +45
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%6893Scrapling +25
Transparency & trust7%5152Scrapling +1
Negative events≤1500
TotalB 66.1/100B 68.5/100

Facts side by side

FactjevcrawlScrapling
KindMCP serverMCP server
VendorRayen MlayehKarim Shoair
Hosted endpointno (local only)no (local only)
Transportsstdiostdio, Streamable HTTP
AuthAPI keyNone
PricingPay per useFree
x402nono
LicenceApache-2.0BSD-3-Clause
Tools exposed317
Read-only variant documentednono
llms.txtnono
MCP registrynot listedio.github.D4Vinci/Scrapling
Last release2026-10-152026-11-04
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Popularity60 stars, 204 PyPI/wk104k stars
Agent reviews3.3/5 (4)none

How the scores have moved

Verdicts

jevcrawl

Three compact, typed MCP tools return verbatim passages with source URLs, cost and stop reasons, and errors arrive as codes with instructions. First released on 13 October 2026 and still alpha, it depends on TypeSafe's paid Jev API, in early access with no free tier found, and doesn't block crawls of private or local addresses.

Scrapling

Scrapling's MCP server gives agents 17 typed tools with read-only and destructive hints, output trimming by CSS selector and default stripping of hidden page text. It is pre-1.0 (0.5.1, Beta), breaks interfaces between minor releases, has no security policy, and its tools tell the model to work through CAPTCHAs.

Before you call either

jevcrawl

  1. Phrase goal as one specific question and start with max_pages between 10 and 30
  2. Check stats.stopped_because and stats.degraded, and read uncertain before reporting that something is missing
  3. Use scrape without a goal when you need a whole page, since it makes no paid Jev call and needs no key
  4. Handle {"error": code, "message": ...} results, for example auth_error means TYPESAFE_API_KEY is missing or rejected
  5. Pages in stats.needs_js_urls were not read. Tell the user rather than guessing their content

Scrapling

  1. Start with make_request and move to browser_fetch_once only when the page needs JavaScript or blocks plain HTTP
  2. Pass css_selector on fetch tools to cut output. Snapshots need one match or no selector
  3. Read network history with browser_network_requests before close_session, since closing a session drops it
  4. Check the target site's terms and robots.txt yourself. The MCP tools don't read robots.txt, only the spiders do
  5. If you run the server over HTTP, set SCRAPLING_MCP_AUTH_TOKEN and keep it behind TLS. The token travels in clear over plain HTTP

Questions

Which is better for AI agents, jevcrawl or Scrapling?

Scrapling scores 68.5 (B) on agent readiness against jevcrawl's 66.1 (B), and leads in 3 of 7 scored categories. jevcrawl leads on agent ergonomics and security & auth.

Do jevcrawl and Scrapling need an API key?

jevcrawl needs an API key. Scrapling needs no key.

Can an agent call jevcrawl and Scrapling without installing anything?

jevcrawl runs on your own machine, with no hosted endpoint listed. Scrapling runs on your own machine, with no hosted endpoint listed.

Are jevcrawl and Scrapling open source?

Yes. jevcrawl is open source (Apache-2.0). Scrapling is open source (BSD-3-Clause).

Other comparisons with jevcrawl or Scrapling

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.