Saleor API + MCP by Saleor

# Fix list: Saleor API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/saleor, the October 2026 research run, assessed 1 October 2026. Grade B, 68.7 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 Saleor 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. Reliability, 50 out of 100, up to 10 more on the total

Why it scored 50: Graded on Saleor Cloud. Status page at status.saleor.io with an incident feed (20). Two incidents in the last 90 days, a "US-EAST-1 disruption" on 6 July with no duration given, and failed logins to Console and Dashboard overnight on 13 July from one of three Keycloak replicas, with transactions unaffected. Without the length of the first we score between minor and major (15). Cloud API use runs under a "fair API usage policy" with no request rates. The only numbers are server caps of 50,000 query complexity, 100 items a page and 4 mutations per request (5). No 429 or backoff guidance found (0). No SLA on the pricing page (0). 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.

## 2. Payments & pricing, 45 out of 100, up to 6.9 more on the total

Why it scored 45: No x402, MPP or L402 (0). Cloud plans are public, Select $1,599 a month to $200,000 GMV and Volume $3,999 to $1,000,000, with 0.8% and 0.4% overage, but there's no per-call or per-unit price (10). The BSD core is free to self-host, and Cloud sandboxes are free for non-commercial use with no card mentioned (20). An agent can run the core from the Docker image with no account, but Cloud needs a browser signup (15).

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, 71 out of 100, up to 5.1 more on the total

Why it scored 71: App tokens limited to named permissions such as MANAGE_PRODUCTS and MANAGE_ORDERS, revocable through the API, and short-lived staff JWTs with refresh. Tokens travel in headers, never the URL (27). The MCP server never runs mutations, and a self-run copy can pin allowed API domains with ALLOWED_DOMAIN_PATTERN (16). Tools return merchant- and shopper-entered text, marked openWorldHint, with no prompt-injection guidance found (5). Observability webhooks can report API calls, but no operator audit log of who did what was found (8). SECURITY.md routes reports through GitHub advisories or security@saleor.io, nine advisories were published between January and July 2026, and the pricing page claims SOC 2 Type 2 and PCI DSS. No security.txt and no bounty (15).

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

Why it scored 86: GraphQL field selection sizes every response, and the MCP server has 8 compact tools (25). Cursor pagination capped at 100, with `filter`, `where`, `search` and sort inputs (20). Mutations return typed `errors` with a code, field and message (18). Payment transaction mutations take an `idempotencyKey`, and 7 of the 8 MCP tools declare readOnlyHint and idempotentHint (the eighth only returns the API URL) (15). MCP tools default to 100 items and need only a channel. The official SDK is a TypeScript app SDK, with no general client in a second 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, 77 out of 100, up to 2 more on the total

Made of editorial 83, provenance 71.

Why it scored 77: BSD-3-Clause core, with the MCP server under AGPL-3.0 (30). Privacy policy updated 8 August 2025 names Saleor Commerce sp. z o.o. in Wrocław, links a subprocessor list and states 30 days for cookies, but no DPA is linked from it and other retention is "not longer than necessary" (20). Deprecations are marked in the schema and removed in a named later version, with upgrade guides, but notices carry versions rather than dates (15). Self-hosted servers send daily usage telemetry by default (counts of products, attributes and models, plus version), described on a Usage Telemetry docs page and turned off with SEND_USAGE_TELEMETRY=False. Cloud subprocessors are listed (18).

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: saleor.io, registered 2018-12-28 (7 years) (11 of 15)
- Endpoint on the vendor's domain:  is not on saleor.io (0 of 15)
- security.txt: not found (0 of 10)

## 6. Schema & documentation, 89 out of 100, up to 1.8 more on the total

Why it scored 89: One GraphQL schema with introspection, and a 954 KB SDL copy in the MCP repo (25). llms.txt split into per-section indexes (10). Fields and mutations carry descriptions, doc categories and deprecation reasons, but rarely say when not to use them (13). Strict GraphQL types with 78 error-code enums and required markers (14). Typed error codes on every mutation payload, with examples in the docs (12). CHANGELOG with a breaking changes section per minor version, GitHub releases, and 464 `@deprecated` markers in the schema (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. Maintenance & community, 85 out of 100, up to 1.3 more on the total

Why it scored 85: 3.23.37 tagged on 30 September 2026 (30). Thirteen 3.23 patch releases between 5 August and 30 September, plus 3.22 patches (20). 194 open issues, with feature requests from June and July still labelled triage (15). The official TypeScript app SDK exists, and the MCP server isn't in the official registry (10). Tests, end-to-end, migration, semgrep and licence workflows on every pull request, and weekly dependency bumps in the MCP repo (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.

## Deductions

Each comes off the total. A fixed and documented problem counts for less at the next check.

- Two high-severity advisories in the last 12 months touched customer data, an IDOR in the GraphQL API published 23 January 2026 (GHSA-r6fj-f4r9-36gr) and account pre-hijacking through an unverified anonymous order merge published 27 July 2026 (GHSA-6whj-8p3f-2xqp). Both were fixed and disclosed in public, so the deduction is small (https://github.com/saleor/saleor/security/advisories).

## 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.

- How long the 6 July 2026 US-EAST-1 disruption lasted
- unchecked: the numbers behind Saleor Cloud's fair API usage policy
- Whether Saleor will publish the MCP server to the official registry or add write tools

## Weaknesses

- The MCP server can't create checkouts or orders
- The hosted MCP at mcp.saleor.app only connects to saleor.cloud stores on 3.21 or later
- Cloud starts at $1,599 a month, and free sandboxes are non-commercial only
- No published request-rate limits, 429 guidance or SLA
- Self-hosted servers send usage telemetry by default

## 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.

- Pass the channel slug on product and checkout queries. Prices and availability are per channel
- Send X-Saleor-API-URL and X-Saleor-Auth-Token on every MCP request, with a token holding MANAGE_PRODUCTS and MANAGE_ORDERS
- Read the `errors` array in every mutation payload. A 200 response can still carry a CheckoutErrorCode
- Keep queries under the 50,000 complexity cap and 100 items a page, and send at most 4 mutations per request
- The 3.24 changelog removes the old dummy payment plugins, so test checkouts should use a payment app

## What the review panel asked for

- Checkout tools on MCP
- Published rate limits
- read-only app permissions
- operator audit log

## 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.