commercetools

# Fix list: commercetools

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/commercetools, the October 2026 research run, assessed 8 October 2026. Grade BB, 71.3 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 commercetools: 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, 20 out of 100, up to 10 more on the total

Why it scored 20: No x402, MPP or L402 in the docs or pricing page (0). The pricing page describes order-based pricing with no figures and sends buyers to sales (0). A 60-day trial with every core commerce API, and the trial FAQ says no credit card or payment is needed (20). A person fills in a web form and follows an emailed link to create the account. API Clients can then be created through the API (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.

## 2. Reliability, 73 out of 100, up to 5.4 more on the total

Why it scored 73: Graded on the HTTP API with the hosted lines. status.commercetools.com lists seven components across five regions with a dated history (20). From 10 July to 8 October 2026 the API component shows elevated 5xx errors in Europe (Google Cloud) on 10 July from 00:49 to 02:30 UTC and two shorter error spikes there on 30 July (41 and 51 minutes). One region of five was affected each time and all three were marked partial or lower, which we read as between minor and one major (15). The docs say the HTTP API has no single documented platform-wide rate limit. Numbers exist for query size (500 per page, offset 10,000), the Knowledge MCP (100 requests per 15 minutes per IP) and Managed MCP Servers (1,000,000 tool calls a project a month) (5). Retry guidance covers 502 and 503 with exponential backoff, Retry-After, and 409 handling through resource versions. There are no idempotency keys (13). 99.9 per cent monthly availability with service credits of 10 to 50 per cent, though Managed MCP Servers are excluded (10). The API and Managed MCP Servers are not marked 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.

## 3. Security & auth, 70 out of 100, up to 5.3 more on the total

Why it scored 70: OAuth 2.0 client credentials through API Clients with view and manage scopes per resource and per store, tokens that last 48 hours by default, an RFC 7009 revocation endpoint, and no tokens in URL parameters. Each managed MCP server has its own scope, `mcp:{projectKey}:{mcpServerKey}`, with tokens capped at 30 days (28). Read-only scopes and tool sets, per-server tool lists, field redaction, and an Identity mode that filters tools by the signed-in user's permissions. No confirmation step for destructive tools was found (15). Tool results carry merchant and shopper text. The docs explain the confused deputy risk and field redaction but give no prompt-injection guidance (6). Audit Log Basic records Merchant Centre changes only. Changes through the API need the Audit Log Premium add-on, and MCP usage tracking needs the Platform Insights add-on (9). SOC 2, ISO 27001 and Cyber Essentials are listed on the security page, with reports under NDA. The Commerce MCP repository has a SECURITY.md that asks for email reports. No security.txt (404) and no bug bounty found, and the trust centre refused our reader (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, 83 out of 100, up to 2.8 more on the total

Why it scored 83: REST queries take limit, offset, sort, where predicates and reference expansion, and GraphQL selects fields. Commerce MCP lists 122 tool names, which is heavy, but an administrator picks the tools per server, `read_all` gives a read-only set, fields can be filtered, and the self-hosted package loads tools on demand above 30 (20). Pagination, filtering and limits on every query endpoint (20). JSON errors with named codes per status. Errors from the load balancer can be HTML or empty (17). Updates and deletes need the resource version, which makes a repeated write fail safely, and MCP tools carry readOnlyHint, destructiveHint and openWorldHint from 1 October 2026. No idempotency key for creates (13). SDKs for Java, TypeScript, PHP and .NET. Changes go through typed update actions, which take more parameters than a plain patch (13).

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, 86 out of 100, up to 2.3 more on the total

Why it scored 86: OpenAPI 3.0 file of 3.1 MB with 822 operations in commercetools/commercetools-api-reference, updated on 7 October 2026, with RAML and a GraphQL schema beside it (25). llms.txt, and every docs page is served as Markdown at the same path with .md (10). The API reference describes each resource, field and update action, and a Knowledge MCP searches the docs and validates requests. Guidance on when not to use a call is thin (14). Typed drafts and update actions with required fields, enums and length limits (13). Error codes are listed by HTTP status with type definitions, and the guides carry request and response examples. The OpenAPI file itself has few examples (12). The API is versionless by policy, with dated release notes and an RSS feed. The managed MCP server follows semver with pinned major versions (12).

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. Transparency & trust, 81 out of 100, up to 1.7 more on the total

Made of editorial 75, provenance 86.

Why it scored 81: Closed service under a public Master Service Agreement and a public 60-day trial agreement. The SDKs are MIT or Apache 2.0 and Commerce MCP is MIT (17). A privacy notice with a section for customers, a public DPA last updated 1 October 2024 and a sub-processor list. The DPA says personal data is deleted promptly at termination without a period in days, and the security page says the DPA is available on request while it is published at commercetools.com/dpa (22). Breaking changes are announced three months ahead and removals six months ahead in release notes, and a deprecations archive gives dates. The policy keeps a right to make larger changes with direct notice (16). Sub-processors listed with purpose, hosting location and product, updated 24 August 2026 (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):

- Terms of service: read, states 6 of the 7 things a reader expects, and has 1 clause that costs points (7.1 of 10)
- Privacy policy: read, states 7 of the 8 things a reader expects (9.3 of 10)
- security.txt: not found (0 of 10)

## 7. Maintenance & community, 85 out of 100, up to 1.3 more on the total

Why it scored 85: Release notes dated 7 October 2026 (30). More than twenty dated entries since 21 September alone (20). Public release notes with RSS, and standard support with published first-response targets of 12 hours for problems and 48 hours for questions. GitHub issue handling wasn't read (12). Four official SDKs on a monthly schedule, with @commercetools/platform-sdk 9.6.0 published on 5 October 2026 (15). The Commerce MCP repository runs quality and release workflows with changesets, and shipped six tagged releases between 3 August and 30 September 2026. Its server.json still names version 4.1.0 while npm has 4.2.2 (8).

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.

## 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: trust.commercetools.com answered 403 to our reader, so the trust centre's documents and any disclosure policy there were not read
- unchecked: GitHub stars and open issues, because the GitHub API refused us for its rate limit
- unchecked: the Merchant Centre sign-up flow itself, which redirects to identity.commercetools.com. The trial steps are taken from the docs
- unchecked: the wording of individual Commerce MCP tool descriptions and input schemas. The tool list and annotations are taken from the docs
- Whether the 10 July 2026 error period in Europe (Google Cloud) counted as downtime under the SLA. The status page marks it a partial service disruption
- No price of any kind is public, so cost per order or per call could not be established
- The lead was right about the HTTP API, SDKs and managed MCP servers. It did not mention that Managed MCP Servers sit outside the standard SLA

## Weaknesses

- No public price. The pricing page describes order-based pricing and sends buyers to sales
- The docs state that the HTTP API has no single documented platform-wide rate limit
- Managed MCP Servers, AI Hub and Platform Insights are excluded from the standard SLA
- API-wide change tracking needs the paid Audit Log Premium add-on. Audit Log Basic records Merchant Centre changes only
- No security.txt and no bug bounty found, and audit reports are released under NDA

## 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 the auth and API hosts for the project's region, such as auth.europe-west1.gcp.commercetools.com and api.europe-west1.gcp.commercetools.com. There are five regions
- Send the resource's current `version` with every update or delete. On 409 ConcurrentModification, re-read the resource and retry only if the change is still needed
- Retry 502 and 503 with exponential backoff from 200 ms, honour Retry-After, and check Content-Type before parsing an error body
- For MCP, ask for an API Client scoped to `mcp:{projectKey}:{mcpServerKey}` and a server limited to the tools the task needs, not `all`
- Keep page size at or under 500 and offset at or under 10,000. Product Search returns at most 100 per request

## 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.