# Fix list: Amazon Ads API From Anchor Terminal's listing at https://www.anchorterminal.com/tools/amazon-ads-api, the October 2026 research run, assessed 8 October 2026. Grade C, 59 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 Ads 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. Reliability, 45 out of 100, up to 11 more on the total Why it scored 45: Graded on the REST API with the hosted checklist. status.ads.amazon.com publishes current status and a history feed by region and category (20). In the last 90 days the feed lists Amazon DSP performance reporting disrupted for about 8 hours on 16 July, reports degraded from 13 to 15 August and sponsored ads reports disrupted from 1 to 3 September 2026. No campaign management incident is listed, so we scored 5 instead of 0 for several majors (5). Rate limits are dynamic and based on system load, with no numbers (0). 429 carries Retry-After and the docs give exponential backoff guidance, but no general idempotency key was found (10). No SLA found for the API (0). The API is generally available. The MCP server is in open beta (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. ## 2. Payments & pricing, 40 out of 100, up to 7.5 more on the total Why it scored 40: No x402, MPP or L402 (0). Amazon states publicly that the API has no fee, with campaign spend and selling account fees billed separately (20). API use is free and test accounts have no active billing (20). A person must create a developer account, apply for access and complete an advertiser's browser consent (0). 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. ## 3. Security & auth, 60 out of 100, up to 7 more on the total Why it scored 60: OAuth 2.0 through Login with Amazon, 60-minute access tokens, revocable grants and 365-day refresh tokens from 30 July 2026. The MCP server supports OAuth 2.1. One scope, advertising::campaign_management, covers most reads and writes (24). Access follows the authorising user's account permissions, which include view-only roles, campaigns can be created PAUSED and test accounts exist. No confirmation step for writes or deletes was found (10). Responses are mostly the advertiser's own data, with shopper search terms in reports. No injection guidance found (7). The API integration dashboard shows call volume, throttling and errors by hour, with no per-call log found (7). Amazon's bug bounty on HackerOne is named in security.txt on amazon.com, which has no Expires field. No SOC 2 or ISO 27001 statement for Amazon Ads was found (12). 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. Agent ergonomics, 62 out of 100, up to 6.2 more on the total Why it scored 62: Query operations take maxResults and nextToken, and reports are requested with chosen columns. The regular MCP endpoint documents 110 tools (5), and the Lite endpoint reduces that to three (add 10) (15). Typed filters and pagination on query operations, plus exports for bulk reads (20). ErrorCode enum with descriptions and 207 responses that index each failed item (17). No general idempotency key was found, and the MCP docs don't mention readOnlyHint or destructiveHint (6). No official SDK. Each call needs up to three headers, a profile ID and the correct regional host (4). 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. ## 5. Schema & documentation, 76 out of 100, up to 3.9 more on the total Why it scored 76: OpenAPI 3.0.1 files download without a login. The merged Ads API v1 file has 104 operations and 1,729 schemas (25). No llms.txt, and the docs site returns a JavaScript shell to a plain fetch (0). Operation descriptions are short, such as "Create campaigns", and list required permissions. When to use an operation is left to the guides (10). Typed inputs with enums, required fields and bounds such as maxResults 1 to 1,000 (14). An ErrorCode enum with a description per code and typed responses per status. Guide examples exist, though fewer sit in the specification (12). Per-resource versioning policy and dated release notes with an RSS feed (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. ## 6. Maintenance & community, 65 out of 100, up to 3.1 more on the total Why it scored 65: Latest dated release note 5 October 2026 (30). 41 dated release notes between 10 July and 5 October (20). Closed service with a release notes feed and a GitHub repository with issues and discussions. We did not read reply times (10). No official SDK, and no Amazon-published entry appeared in the first 50 MCP registry results for "amazon" (0). The docs repository had 13 commits since 10 July, the latest on 30 September, with no CI (5). 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. ## 7. Transparency & trust, 73 out of 100, up to 2.4 more on the total Made of editorial 51, provenance 94. Why it scored 73: Closed service with a published licence agreement, last updated 1 June 2024, and MIT-0 samples (15). The Data Protection Policy sets rules for developers handling Amazon data, such as deletion within 72 hours of a request. The Amazon.com Privacy Notice, last updated 30 June 2026, applies. No API-specific retention periods or DPA were found (12). The versioning policy promises six months' notice before a shutoff, and release notes date deprecations. The licence agreement also reserves the right to modify or discontinue without notice (18). Three regional hosts are documented. No subprocessor list was found (6). 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: published, but our reader couldn't read it (7 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) ## 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. - unchecked: numeric rate limits. The docs describe them as dynamic and give none - unchecked: whether MCP tools carry readOnlyHint or destructiveHint annotations. We read the docs, not a live tools/list response - unchecked: MCP registry beyond the first 50 results for "amazon" - unchecked: retention periods in the Amazon.com Privacy Notice, and any DPA or subprocessor list for Amazon Ads - unchecked: reply times on GitHub issues and discussions for amzn/ads-advanced-tools-docs - unchecked: SOC 2 or ISO 27001 coverage for Amazon Ads - The release notes feed carries one entry dated 30 October 2026 (Review Requests API beta), after the check date. We used 5 October 2026 as the latest release ## Weaknesses - Access needs an approved application (review may take up to one business day) and an advertiser's consent in a browser - Rate limits are dynamic and based on system load, with no published numbers - Status feed lists reporting interruptions on 16 July, 13 to 15 August and 1 to 3 September 2026 - No official SDK. The docs describe generating a client from the OpenAPI files - One OAuth scope, advertising::campaign_management, covers most reads and writes - No llms.txt, and the documentation site returns a JavaScript shell to a plain fetch ## 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 Amazon-Advertising-API-ClientId and a Bearer access token on every call, and Amazon-Advertising-API-Scope with a profile ID from GET /v2/profiles on most - Call the host for the advertiser's region. advertising-api.amazon.com is North America, advertising-api-eu Europe and advertising-api-fe Far East - Refresh the access token every 60 minutes. Refresh tokens issued from 30 July 2026 expire 365 days after consent - On 429, wait the Retry-After seconds and back off exponentially. Request an export instead of listing every entity - Rehearse writes in a test account, or create campaigns in the PAUSED state, before anything can spend - For MCP, prefer https://advertising-ai.amazon.com/mcp/lite and disable delete tools in the client configuration ## 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.