What did Hlido score AgentScrape?

AgentScrape scored 69/100 (FADING) in Hlido's independent, hands-on review.

Does any vendor pay Hlido for placement?

No. Hlido takes no money from the agents it rates — scoring weights stay private and the evidence behind every verdict is public.

AgentScrape

Name: AgentScrape review
Item: AgentScrape
Rating: 69
Author: Hlido Editor

Infrastructure · tested 2026-08-14 · by the Hlido desk, not the vendor

In short: A scraping API that serves its own machine-readable manifest as its homepage and prices every tool at $0.001 in on-chain USDC — genuinely agent-native, and almost unusable for a human evaluating it.

Visit AgentScrape → scorecard.json

Quick answer

AgentScrape scores 69/100 (FADING) on Hlido’s independent, hands-on test (reviewed 2026-08-14). FADING because most of the checks fail on the human-facing side: no documentation surface, no terms, no operator accountability, and no statement on scraping conduct or data handling — for a scraping service, that last g Pricing: Usage-based · Free tier (free entry point documented).

Hlido Editor · 2026-08-14

AgentScrape is the most literally agent-first surface in this batch: the root URL returns a JSON manifest, not a marketing page. That manifest is substantive — it enumerates six HTTP endpoints and six MCP tools, publishes a per-call price of $0.001 for every tool, names the payment network (Base, eip155:8453), the x402 facilitator, the payTo address, the free tier (10 calls per wallet per 30 days), the transport (MCP Streamable HTTP) and even the extraction model (Llama 4 Scout via Groq). By the standard Hlido applies to machine consumers, this is close to exemplary: an agent can discover capability, price and payment path in one unauthenticated request, with no signup and no API key. The trade-offs are real though. There is no human-readable surface at all — no docs site, no examples, no error-semantics reference, no terms, no operator identity beyond a GitHub org and a wallet address. Payment is USDC on Base via x402, which is an elegant fit for autonomous agents and a hard requirement for everyone else. And the model that matters most for a scraping service — what it does about robots.txt, rate limits, blocked targets or legal exposure — is not addressed anywhere. The score is held down by that missing half, not by the design choice: the agent-facing manifest is strong, and the surrounding operational and accountability story is absent.

Why FADING

FADING because most of the checks fail on the human-facing side: no documentation surface, no terms, no operator accountability, and no statement on scraping conduct or data handling — for a scraping service, that last gap is material. Not lower, and close to the band above, because the machine-readable manifest is genuinely excellent: complete capability, transparent per-call pricing and a working no-signup path, all discoverable in a single unauthenticated request.

What we saw

1 screenshot captured by the Hlido engine during the reviewed run (run-a21d27538264070b-agent-scrape-healingsunhaven-workers-dev). Our own captures — not vendor marketing material.

AgentScrape — run screenshot 1 (home.png) — home.png

What it does well

Root URL returns a complete machine-readable capability manifest — no signup, no key, no negotiation
Per-call pricing published for every single tool ($0.001), which is rarer than it should be
Both HTTP and MCP surfaces exposed, with all endpoints and tool names enumerated
Free tier stated precisely (10 calls per wallet per 30 days) with the identifying header named
Extraction model disclosed (Llama 4 Scout via Groq) rather than hidden behind 'AI-powered'

What it fails at

No human-readable documentation, examples or error-semantics reference anywhere
No terms of service, acceptable-use policy or operator identity beyond a wallet address
Nothing stated about robots.txt handling, rate limiting or blocked targets — the core conduct question for a scraper
Payment is USDC on Base only; no conventional payment path exists
No uptime, support or contact channel published

Red flags

A scraping service with no published position on robots.txt, rate limiting or prohibited targets pushes the entire conduct and legal risk onto the caller, silently.
Operator accountability is a GitHub organisation and a wallet address. There is no company identity, terms of service or support channel — for a paid service, that is a thin basis for reliance.
The free tier is keyed on an x402 payer header rather than an account, so the 10-call limit is only as strong as wallet identity makes it.

Best for

Autonomous agents that need to buy scraping capability without a human doing signup or billing
Developers already operating on Base with USDC who want per-call metered scraping
Prototypes and experiments where the 10-call free tier is enough to evaluate

Not recommended for

Companies with procurement, invoicing or vendor-accountability requirements — none of that exists here
Any use where scraping conduct and legal exposure need a documented position
Teams without on-chain payment capability; there is no alternative rail

Pricing & access

ModelUsage-based · Free tier
Free entry pointYes — a free tier or open-source edition is documented
Price points we recorded…its own machine-readable manifest as its homepage and prices every tool at $0.001 in on-chain USDC — genuinely agent-native, and almost unusable for a human…

Derived from Hlido-held evidence only (engine checklist + editorial text); quotes are verbatim from the scorecard; not vendor-supplied; re-derived daily. Verify current prices on the vendor's pricing page. Last verified 2026-08-11.

Compared to

Firecrawl accountability-vs-autonomy
Firecrawl is the documented, conventionally-billed incumbent with real terms and support. AgentScrape is cheaper per call and needs no signup, but has none of the accountability. Choose Firecrawl for anything a company depends on, AgentScrape for autonomous or experimental use.
Apify platform-vs-primitive
Apify is a full platform with a marketplace, scheduling and compliance posture; AgentScrape is six endpoints and a price list. Not really competitors except at the narrowest point of 'fetch me this page'.

Agent relevance

API MCP Behavioral-testable

Agentic-Commerce Readiness 49/100 · SURFACE-ONLY

Independent readiness for agent delegation & transaction. How it’s scored · check live

Among the most agent-addressable surfaces reviewed: an unauthenticated JSON manifest enumerating every endpoint, tool and price, an MCP Streamable HTTP transport, and machine-native payment via x402 that removes the human signup step entirely. An agent can discover, price and pay for capability without a person in the loop.

Agent-friendly score: 9/10

Evidence

Homepage publicly accessible and value proposition clearly stated — source (2026-08-14) verified
Pricing page discoverable in 2 clicks from homepage — source (2026-08-14) verified
Documentation or live demo accessible without login — source (2026-08-14)
Integration list or supported frameworks documented — source (2026-08-14) verified
Authentication / data handling claims publicly stated — source (2026-08-14)

scorecard.json · transparency passport · registry · methodology

More: compare agents · best of · developer tools · incident registry

Verdict by Hlido Editor, our automated editorial system · Method: public-surface-tier-2+editorial-narrative-v2 · Methodology version 2026.08 ·

How this page was produced. The scores, claim verdicts and evidence come from automated hands-on testing of the product’s public surface. The written analysis is drafted by an AI system, and pages publish without a person reviewing each one. Hlido publishes this record and answers for it — tell us if anything here is wrong and we will correct it.

Embed this trust badge

Live, always-current independent score — free to embed on your site or README. No vendor pays for placement.

Markdown

[![Hlido trust score](https://hlido.eu/badge/hshintelligence-agent-scrape.svg)](https://hlido.eu/check/?agent=hshintelligence-agent-scrape)

HTML

<a href="https://hlido.eu/check/?agent=hshintelligence-agent-scrape"><img src="https://hlido.eu/badge/hshintelligence-agent-scrape.svg" alt="Hlido trust score"></a>