Shopify API + MCP by Shopify

# Fix list: Shopify API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/shopify, the October 2026 research run, assessed 1 October 2026. Grade BB, 75.2 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 Shopify 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, 40 out of 100, up to 7.5 more on the total

Why it scored 40: No x402, MPP or L402. UCP checkout uses the buyer's normal payment methods (0). Plan prices are public, Basic $39, Grow $105 and Advanced $399 a month, per the 30 September check (10). Development stores are free for building and testing, per the 30 September check (20). Catalogue and cart calls need only an agent profile URL in the request, but checkout needs authentication or signing and back-office access needs a person to create an app (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, 73 out of 100, up to 5.4 more on the total

Why it scored 73: Atlassian Statuspage at shopifystatus.com with Admin, Checkout, Storefront, API & Mobile and other components, and a history page (20). The front page shows no incidents from 17 September to 1 October. The history page renders with JavaScript and the incidents API is closed to our fetcher by robots.txt, so earlier history is unchecked, and the page itself says issues affecting a small share of stores may not appear. A clean partial window earns half (15). Limits are published per API, a 40-request REST bucket refilling at 2 a second (10 times that on Plus) and a cost-based GraphQL bucket sized by plan, per the 30 September check, since the GraphQL reference page was refused by our fetch rate limit (15). The limits guide says to stop and back off one second when throttled, every response carries throttle metadata, and the UCP spec requires an Idempotency-Key on checkout writes (13). No SLA found. The pricing page was refused by our rate limit, so this is unchecked (0). Admin and Storefront APIs 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.

## 3. Security & auth, 71 out of 100, up to 5.1 more on the total

Why it scored 71: Per-app access tokens limited by granular read and write scopes, OAuth for public apps, separate storefront tokens, and token exchange for offline tokens (27). Read-only scopes per resource, Checkout MCP calls must be authenticated or signed, and the Dev MCP server only reads docs and schemas (16). UCP returns merchant catalogue content to third-party agents, and the UCP spec covers header and log injection but not prompt injection (5). The Dev Dashboard flags each app's deprecated calls, but no general API audit log was checked (5). security.txt points to a HackerOne programme with an acknowledgements page, a security@shopify.com contact and a PGP key, though it has no Expires field per the 30 September check (18).

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, 79 out of 100, up to 3.4 more on the total

Why it scored 79: GraphQL field selection sizes every Admin and Storefront response. UCP splits shopping into 13 tools across catalogue, cart, checkout and order (22). Cursor pagination with `first` and `after` and a `query` filter syntax on list fields (20). `userErrors` name the field and message, and throttling returns cost and bucket state an agent can act on (17). UCP checkout tools require an idempotency key. MCP tool annotations and Admin idempotency weren't checked (10). Official libraries are JavaScript packages in this listing. Every UCP call must carry an agent profile in `meta` (10).

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, 92 out of 100, up to 1.3 more on the total

Why it scored 92: Fully typed GraphQL Admin and Storefront schemas with introspection, and UCP tools defined by published JSON schemas (25). shopify.dev/llms.txt is a single long Markdown guide rather than an index (10). GraphQL fields and the UCP spec describe each operation's purpose, with some when-to-use guidance in the guides (15). Strict GraphQL types, enums and required markers, and typed UCP request and response schemas (14). Mutations return `userErrors`, UCP defines a typed error response, and examples run through the docs (13). Quarterly dated API versions, each supported at least 12 months with 9 months of overlap, and a changelog with action-required tags (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, 85 out of 100, up to 1.3 more on the total

Why it scored 85: Changelog entries on 30 September 2026 (30). Fifteen entries between 21 and 30 September alone (20). Public changelog with action-required and breaking tags, developer forums and partner support (13). Current official SDKs, @shopify/shopify-api last released on 25 September per the 30 September check, and @shopify/dev-mcp at 1.16.0. No Shopify server in the official MCP registry (15). Dev MCP pins current dependencies such as @modelcontextprotocol/sdk 1.29.0. SDK CI not checked (7).

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, 91 out of 100, up to 0.8 more on the total

Made of editorial 81, provenance 100.

Why it scored 91: Closed platform with published terms, and open-source client libraries (15). Privacy policy updated 7 July 2026, store data kept for two years after a store closes before deletion begins, a published subprocessor list and a processor policy for transfers (26). Each API version is supported at least 12 months, deprecated calls are flagged in the Dev Dashboard, and breaking changes are tagged with the API version they land in, such as marketCurrencySettingsUpdate removed in 2027-01 (20). Subprocessors listed and data flows named by region, through Ireland for the EEA, Canada and the US, and Singapore for Asia-Pacific (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.

## 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 (JavaScript-rendered history, robots.txt on the incidents API)
- unchecked: the UCP and Storefront MCP pages, the GraphQL Admin reference and the pricing page, all refused by our fetch rate limit
- Whether Shopify publishes an uptime SLA for Plus
- Whether Shopify's UCP tools carry readOnlyHint or destructiveHint annotations

## Weaknesses

- Closed platform. You can't self-host or change checkout internals
- Agent surface changes often. Storefront MCP tools moved to UCP, and AI Toolkit skills were consolidated on 25 September 2026
- Checkout calls need signing or authentication, more setup than a plain key
- No Shopify server in the official MCP registry
- Third-party payment providers cost 0.2 to 2 per cent extra per order

## 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.

- Pin an API version in the URL and plan to move at least once a year. Old versions fall forward to the oldest supported one
- Read the throttle status in each response's cost extension and back off one second when throttled
- Send an agent profile in `meta` on every UCP call, and an idempotency key on every checkout write
- Check `userErrors` on every mutation. A 200 response can still carry a failed write
- Add @shopify/dev-mcp while writing code so the agent checks queries against the current schema

## What the review panel asked for

- State trial card terms
- dated notices for MCP changes
- one fee page
- when-not-to text
- an indexed llms.txt
- an llms.txt index
- Publish an uptime SLA for Plus
- readOnlyHint on UCP tools
- Stable UCP docs pages
- UCP prompt-injection guidance
- annotations on UCP tools

## 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.