Amazon Creators API

# Fix list: Amazon Creators API

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/amazon-creators-api, the October 2026 research run, assessed 14 October 2026. Grade D, 48.7 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 Amazon Creators API: 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. Payments & pricing, 10 out of 100, up to 11.3 more on the total

Why it scored 10: No x402, MPP or L402 (0 of 40). The documentation states no fee for API calls, and usage limits are tied to referred revenue, not a price list. Nothing says the API is free in plain terms, so half the line (10 of 20). There is no free tier in the usual sense. Access needs an accepted Associates account and 10 qualifying sales in the trailing 30 days, so a new developer cannot start (0 of 20). Associates signup, final acceptance and credential creation all happen in a browser by the primary account owner (0 of 20). Total 10.

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.

## 2. Reliability, 45 out of 100, up to 11 more on the total

Why it scored 45: No status page for the Creators API was found in the documentation (0 of 20). No readable incident history, so the line takes the 5-point default (5 of 30). Rate limits are published with numbers, 1 request a second and 8,640 a day at the start, then scaled by shipped revenue up to 10 a second (15 of 15). 429 ThrottleException and 500 InternalServerException both tell clients to retry with exponential backoff, errors can carry retryAfterSeconds, and every operation is a read, so retries are safe (15 of 15). No SLA (0 of 10). The API is the supported successor to PA-API 5 and generally available (10 of 10). Total 45.

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. Security & auth, 48 out of 100, up to 9.1 more on the total

Why it scored 48: OAuth 2.0 client credentials with tokens that last one hour. Two credentials per application allow rotation, and credentials can be deleted, but there is one scope (creatorsapi::default) and no finer permissions (22 of 30). The API is read-only, so an agent cannot spend money or change an account through it (18 of 20). It returns product titles and feature bullets written by sellers, with no guidance on treating them as untrusted data (5 of 15). The operator sees attributed sales in the Link Type Performance report, not a per-call log (3 of 15). Programme not established. security.txt on www.amazon.com was not read because robots.txt disallows our crawler, affiliate-program.amazon.com has none (404), and the HackerOne page for Amazon's programme did not render, so no point was given (0 of 20). Total 48.

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.

## 4. Schema & documentation, 50 out of 100, up to 8.1 more on the total

Why it scored 50: No public OpenAPI or other machine-readable description was found. The SDKs are generated archives behind a download (0 of 25). No llms.txt (/creatorsapi/docs/llms.txt returns 404) and no Markdown twins (0 of 10). Each operation page states its purpose, the parameters that apply to which search indices and when to use a browse node instead of a keyword, without when-not-to-use guidance (14 of 20). Parameters are typed with defaults, ranges (itemCount and itemPage 1 to 10) and required markers, and resources are a fixed enum of dot paths (12 of 15). Examples in cURL and JSON for each operation, and an error page listing every exception with its reason codes and example messages (14 of 15). The API version is in the path (v1) and the SDK changelog is dated, but there is no changelog for the API itself (10 of 15). Total 50.

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.

## 5. Maintenance & community, 41 out of 100, up to 5.2 more on the total

Why it scored 41: The latest dated change is SDK 1.3.0 on 21 August 2026, 54 days ago (20 of 30). Only one dated entry falls in the last 90 days (0 of 20). Support is through the Associates contact form, which promises a reply to acceptance requests in 3 to 4 days, and there is no public API changelog or forum (8 of 15). Official SDKs in four languages are current to August 2026, but none is published on npm, PyPI, Packagist or Maven by Amazon (10 of 15). The npm names creatorsapi-nodejs-sdk and amazon-creators-api are held by individuals, and no CI or dependency status is public (3 of 10). Total 41.

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. Transparency & trust, 52 out of 100, up to 4.2 more on the total

Made of editorial 28, provenance 76.

Why it scored 52: Closed service with published terms. The Operating Agreement (updated 15 October 2025), the Program Policies (updated 14 April 2026) and a per-locale IP Licence govern the API (15 of 30). The Operating Agreement points to the Amazon.com Privacy Notice, which sits on amazon.com and was not read because robots.txt disallows our crawler. The policies forbid caching customer information, and caching rules for product data are published (5 of 30). The PA-API 5 deprecation notice explains the 403 response and the migration, but gives no dates or notice period (8 of 20). No subprocessor list or data locations were found for the API (0 of 20). Total 28.

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):

- Terms of service: read, states 6 of the 7 things a reader expects (9.1 of 10)
- Privacy policy: read, states 6 of the 8 things a reader expects, and has 1 clause that costs points (6.5 of 10)
- Status page: not found (0 of 10)
- security.txt: could not be fetched (0 of 10)

## 7. Agent ergonomics, 85 out of 100, up to 2.4 more on the total

Why it scored 85: The resources parameter returns only the fields requested, and the best practices recommend it to cut payload size (22 of 25). SearchItems pages up to 10 items with itemPage 1 to 10, so 100 results at most, with filters for brand, price range, condition, availability, delivery flags, merchant and sort (17 of 20). Errors have a type, a machine-readable reason, fieldList for validation failures and retryAfterSeconds where relevant, and partial results return an errors array per item (18 of 20). All four operations are reads and safe to retry, though no idempotency mechanism is needed or named (15 of 20). Sensible defaults (search index All, availability Available, itemCount 10) and official SDKs in four languages, though only as archive downloads (13 of 15). Total 85.

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.

## 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.

- Held for robots.txt. www.amazon.com/robots.txt disallows Claude-User, ClaudeBot and Claude-SearchBot for the whole site. The Conditions of Use (https://amazon.com/gp/help/customer/display.html?ie=UTF8&nodeId=508088) and the Amazon.com Privacy Notice (https://amazon.com/gp/help/customer/display.html?ie=UTF8&nodeId=468496) are on that host and were not fetched, so the lander may hold this listing.
- unchecked: the Amazon.com Conditions of Use, including any clause on automated access or agents buying on amazon.com.
- unchecked: the Amazon.com Privacy Notice and its retention statements.
- unchecked: Amazon's security.txt and vulnerability research programme. hackerone.com/amazonvrp did not render without JavaScript.
- unchecked: the item-info, parent-asin and variation-summary resource pages, which broke off mid-transfer on the first read. The four operation pages were read in full.
- No official Amazon MCP server, agent checkout programme or public API for Buy for Me, Rufus or Alexa+ open to outside agents was found. The official MCP server found is Amazon Ads, listed separately as amazon-ads-api.
- The PA-API 5 retirement date is not on Amazon's notice. Third-party pages give dates in January and May 2026, which were not used.

## Weaknesses

- No order, cart, checkout, order status or return operation
- Access needs 10 qualifying sales in the trailing 30 days and lapses without them
- No public OpenAPI description, llms.txt or status page was found
- SDKs are archive downloads, and the matching npm package names belong to individuals
- The PA-API 5 deprecation notice gives no dates, and old calls now return 403

## 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.

- Send x-marketplace as a header and marketplace and partnerTag in the body on every call
- Cache the access token for its 3,600 seconds and share it across processes
- Request only the resources the task needs, and use offersV2 for prices, because the older price resource is gone
- Set the user agent to Agent/<name> as the Associates Agent Terms require
- Hand purchases to the person through the returned detailPageURL without editing its parameters

## 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.