Commerce Layer API + MCP by Commerce Layer

# Fix list: Commerce Layer API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/commerce-layer, the October 2026 research run, assessed 1 October 2026. Grade B, 63.9 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 Commerce Layer API + MCP: 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, 25 out of 100, up to 9.4 more on the total

Why it scored 25: No x402, MPP or L402 (0). Only the free Developer plan has a public price. Enterprise is contact sales (5). Developer plan is free with no time limit and no credit card (20). A person signs up in the browser to get credentials (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. Security & auth, 64 out of 100, up to 6.3 more on the total

Why it scored 64: OAuth 2.0 tokens throughout. Integration credentials follow a custom role set per resource and per operation, sales channel tokens are scoped to a market, and the Core MCP accepts the same tokens or runs the OAuth flow (28). The docs tell you to give the agent a dedicated role with minimal permissions, but `delete_resource` has no documented confirmation step (12). Tool results include merchant- and shopper-entered data with no prompt-injection guidance found (5). The versions endpoint, which gave change history per resource, was removed on 8 May 2026. Event stores remain, with a retention policy added on 18 June (6). SOC 2 Type 2, ISO 27001 and PCI DSS Level 1 claimed on the security page, with annual penetration tests and fixes within 90 days. The SDK's SECURITY.md gives two email addresses. No security.txt and no bug bounty found (13).

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.

## 3. Reliability, 70 out of 100, up to 6 more on the total

Why it scored 70: Atlassian Statuspage at status.commercelayer.io with ten components, including Commerce API, Cart and Checkout, and a history link (20). We could read only the last 15 days, which show one planned maintenance on 28 September (06:30 to 07:39 CEST) and nothing else. The incident feed was refused by our fetch rate limit, so the rest of the 90 days is unchecked. A clean partial window earns half (15). Rate limits published per IP, 200 live writes and 1,000 cacheable reads a minute, 50 writes per endpoint per 10 seconds, 30 token requests a minute, half that in test (15). A 429 carries X-Ratelimit-Limit, -Interval and -Remaining, but the docs say no reset header is sent, there's no Retry-After, and no backoff or idempotency guidance was found (7). "Enterprise SLAs" on the pricing page with no figures or terms (3). The API and Core MCP are generally available (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.

## 4. Agent ergonomics, 64 out of 100, up to 5.9 more on the total

Why it scored 64: 11 Core MCP tools, generic list, get, create, update and delete over every resource, with schema discovery instead of one tool per object (20). Filters, sort, include, sparse fieldsets and pagination on list calls (20). JSON:API errors with codes, and the MCP validates filters and writes against the schema before calling the API (16). No idempotency keys, and no readOnlyHint or destructiveHint annotations documented (0). Official JavaScript SDK, generated from the schema. We didn't confirm a second official language (8).

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. Transparency & trust, 59 out of 100, up to 3.6 more on the total

Made of editorial 42, provenance 75.

Why it scored 59: Closed service with published terms, and MIT-licensed SDKs (15). Privacy policy last updated 28 October 2020, with no DPA linked, no subprocessor list and no retention periods beyond "as long as reasonably necessary" (10). One dated deprecation (resource-level meta fields removed on 5 October 2026, announced 17 June), but most breaking changes appear on the day they ship (10). The privacy policy names Intercom, Google, GitHub, Stripe and ConvertKit and transfers to the US, but no hosting regions (7).

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: commercelayer.io, no registry record we could read (0 of 15)
- security.txt: not found (0 of 10)

## 6. Schema & documentation, 79 out of 100, up to 3.4 more on the total

Why it scored 79: OpenAPI 3.0 file served without auth at data.commercelayer.app (25). llms.txt and Markdown docs (10). Core MCP tool descriptions are one line each, and the API reference covers each resource, with little on when not to use a call (13). Typed JSON:API attributes in the spec, but MCP writes take a free-form attributes object that preflight checks against the schema (11). Per-resource examples in the reference and JSON:API error objects (11). A dated public changelog tags breaking changes and deprecations, but there's no API versioning, and four breaking changes shipped between 8 May and 2 September 2026, including removal of the versions endpoint (9).

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. Maintenance & community, 82 out of 100, up to 1.6 more on the total

Why it scored 82: Changelog entry on 29 September 2026 (30). Five dated entries since 3 July, on 10 July, 21 and 27 August, 2 September and 29 September (20). Public changelog and community support on the free plan, dedicated support on Enterprise (10). @commercelayer/sdk 7.12.1 on 17 July 2026, generated from schema 7.10.3. The MCP servers aren't in the official registry (12). SDK repo runs semantic-release, CodeQL and vulnerability-update workflows (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.

## 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: incident history before 17 September 2026 (the history feed was refused by our fetch rate limit)
- Whether the four 2026 breaking changes were announced in advance anywhere other than the changelog entry on the day
- Whether official SDKs exist in a second language

## Weaknesses

- No price between the free plan and a sales-quoted Enterprise contract
- No API versioning, and four breaking changes between 8 May and 2 September 2026
- 429s carry no Retry-After or reset header
- Privacy policy last updated October 2020, with no DPA or subprocessor list linked
- No MCP tool annotations and no confirmation step for delete_resource

## 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.

- Call `get_resource_schema` before any write. Preflight rejects bad filter shapes before they reach the API
- Give the agent an integration credential tied to a narrow role rather than an admin role
- On a 429, wait out the sliding window. No Retry-After is sent, and the IP stays blocked while the rate stays high
- Place an order by PATCHing it with `_place: true` once line items, addresses, shipping and payment are set
- Move reads of `mode`, `organization_id` and `trace_id` to root-level meta before 5 October 2026

## What the review panel asked for

- Retry-After on 429
- Idempotency on writes
- confirmation on `delete_resource`
- tool annotations

## 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.