ScrapeGraphAI by ScrapeGraphAI

# Fix list: ScrapeGraphAI

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/scrapegraphai, the October 2026 research run, assessed 1 October 2026. Grade B, 68.3 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on ScrapeGraphAI: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Security & auth, 39 out of 100, up to 10.7 more on the total

Why it scored 39: OAuth 2.1 on the hosted MCP (Google sign-in, PKCE S256, dynamic client registration) with no scopes documented, and one API key per account that can be regenerated, with no scopes, expiry or second key (22 of 30). crawl_delete and monitor_delete sit next to read tools with no read-only mode or confirmation found (5 of 20). Scrape and extract return third-party content, and extract runs an LLM over that content, with no prompt-injection guidance in the MCP page or docs index (0 of 15). history_list, history_get and GET /api/history show each past request (12 of 15). No security.txt per the 30 September check and no security or compliance page in the docs index (0 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 2. Reliability, 64 out of 100, up to 7.2 more on the total

Why it scored 64: openstatus page at scrapegraphapi.openstatus.dev (20). Only the last seven days were readable, 'no reports within the last 7 days', and last week's check found it still listing v1 services (10 of 30). Rate limits published, but the rate-limits page gives 10, 100, 500 and 5,000 a minute per the 30 September check while the troubleshooting page gives 5, 30 and 100, so the numbers can't both be right (12 of 15). 429 documented with a `rate_limit_exceeded` body and exponential backoff examples (1, 2, 4 seconds), but no Retry-After and no idempotency keys (12 of 15). No SLA found (0). v2 is GA (10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 3. Agent ergonomics, 72 out of 100, up to 4.6 more on the total

Why it scored 72: 20 tools on the hosted MCP server with no tool filtering found (15 of 25). Format selection and paginated crawl pages and history (17 of 20). One error shape with type and message, 402 when credits run out (17 of 20). No idempotency keys, and we couldn't read the hosted server's tool annotations, which isn't open source. The older open-source server annotated every tool (8 of 20). Official Python and JavaScript SDKs, and a scrape needs only a URL (15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 4. Transparency & trust, 61 out of 100, up to 3.4 more on the total

Made of editorial 40, provenance 82.

Why it scored 61: The hosted API and hosted MCP server are closed, while the SDKs, the older MCP server and the scrapegraphai library are MIT (20 of 30). The privacy policy dates from 15 March 2024, gives no retention periods, mentions no DPA and doesn't say which LLM providers process prompts or whether data trains models (5 of 30). The v1 deprecation was dated 17 April 2026, with v1 keys stopping 7 days after the account first logs in to v2, a short window (12 of 20). Data is processed in the United States per the policy, with no subprocessor list (3 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- Domain age: scrapegraphai.com, registered 2024-04-29 (2 years) (7 of 15)
- security.txt: not found (0 of 10)

## 5. Maintenance & community, 70 out of 100, up to 2.6 more on the total

Why it scored 70: Changelog v3.5.0 on 30 July and scrapegraph-py 2.3.2 on 31 July 2026 (20). v3.4.2 on 6 July, v3.5.0 on 30 July and SDK 2.3.0 to 2.3.2 on 30 and 31 July (20). Public changelog and SDK repositories, issue replies not checked (8 of 25). Current Python SDK. The JavaScript SDK's last tag is v2.0.1 from April, with commits to 3 August (12 of 15). The Python SDK runs CI, CodeQL and dependency review (10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## 6. Schema & documentation, 88 out of 100, up to 2 more on the total

Why it scored 88: OpenAPI 3.1.0 at v2-api.scrapegraphai.com/api/openapi.json, info version 2.0.0 (25). llms.txt and Markdown docs (10). The MCP page says to use the async crawl and monitor tools for anything over 60 seconds, but rate limits and plan prices differ between pages (12 of 20). Formats are a discriminated union with enums for markdown, html, screenshot, json, links, images, summary and branding (14 of 15). Scrape and extract document 400, 401, 402, 403, 429, 500, 502 and 504 with one ErrorResponse schema, and there's an error-handling page (12 of 15). Versioned, dated changelog, v3.5.0 on 30 July 2026 (15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 7. Payments & pricing, 90 out of 100, up to 1.3 more on the total

Why it scored 90: x402 on ScrapeGraphAI's own domain mints an account, key and credits (5 USDC for 1,000 credits, 40 for 10,000, 150 for 50,000, USDC on Base), and Orthogonal's gateway at x402.orth.sh/scrapegraph takes per-call x402 on scrape, extract, search, crawl and monitor with no ScrapeGraphAI key. Per-call payment only through a third party, so 30 (30 of 40). Credit costs per operation, plans and non-expiring top-up packs are public (20). Free plan of 500 credits with no card (20). An agent can buy a key over x402 or MPP with no human signup (20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- Which rate-limit table is current, 10/100/500/5,000 or 5/30/100 a minute.
- Status history beyond the last seven days, which the openstatus page didn't show us.
- Orthogonal's per-call prices, which the docs point to a CLI for.
- Whether the hosted MCP tools carry readOnly and destructive annotations; the hosted server isn't open source.

## Weaknesses

- Rate limits and plan prices differ between docs pages
- Privacy policy from March 2024 with no retention periods, DPA or LLM provider list
- One account key with no scopes, and delete tools beside read tools on the MCP server
- No prompt-injection guidance, though extract runs an LLM over scraped pages
- No security.txt or security page

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Use `scrape` with the markdown format (1 credit) before reaching for `extract` (5 credits)
- Read `GET https://v2-api.scrapegraphai.com/api/agent/protocols` for current packs and prices before paying over x402
- MCP tool calls stop at 60 seconds. Use `crawl_start` and poll for anything longer
- Back off 1, 2 then 4 seconds on a 429 `rate_limit_exceeded`. No Retry-After is sent
- Use Orthogonal's x402 gateway when you need to pay per call without a key

## What the review panel asked for

- reconcile the free tier across docs
- publish per-call x402 prices
- source spans for fields
- one rate-limit table

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.