Snipcart API + MCP by Snipcart (Duda)

# Fix list: Snipcart API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/snipcart, the October 2026 research run, assessed 1 October 2026. Grade E, 41.2 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 Snipcart 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. Security & auth, 20 out of 100, up to 14 more on the total

Why it scored 20: One secret key per mode (test or live) with full account access, sent as Basic auth or, for the MCP, in an X-Snipcart-Api-Key header. The MCP docs say OAuth 2.1 isn't supported (12). No scoped or read-only keys, and refund, stock and archive tools carry no documented confirmation (3). Tools return customer and order data, with no prompt-injection guidance found (5). Order logs are notes, not an audit trail (0). No security.txt per the 30 September check, and no disclosure contact in the terms (0).

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.

## 2. Agent ergonomics, 25 out of 100, up to 12.2 more on the total

Why it scored 25: 38 MCP tools with no toolsets or filtering (5). List endpoints and MCP list tools exist, but paging parameters weren't confirmed this run (10). Error format undocumented beyond status codes (5). No idempotency keys and no readOnlyHint or destructiveHint annotations documented, though the tools create refunds and archive products (0). No official API SDK. Setup in Claude Code is one line (5).

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.

## 3. Schema & documentation, 37 out of 100, up to 10.2 more on the total

Why it scored 37: No OpenAPI file, and the MCP source isn't public, so we couldn't read the tool schemas (5). No llms.txt per the 30 September check (0). The MCP docs describe the 38 tools in nine groups by what they do, with no when-not-to-use guidance (8). Tool input types couldn't be checked (5). The REST reference has examples per endpoint, but errors are only described as "a JSON error body on 4xx" (7). Dated release notes every few weeks and a stated change policy, new fields may appear without notice but existing ones aren't renamed or removed (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.

## 4. Reliability, 58 out of 100, up to 8.4 more on the total

Why it scored 58: status.snipcart.com runs Upptime from the public snipcart/status repo, checking four URLs, the merchant dashboard host (app.snipcart.com, which also serves the API), the website, the docs and the support forum. Neither the API path nor the MCP endpoint at ai.snipcart.com is checked on its own (15). Since 3 July the dashboard host shows no downtime, at 100% for the month and year in the summary file, and the docs went down twice, on 21 and 24 September (25). REST rate limits aren't published beyond per-endpoint limits on discount listing and order notifications, and the MCP server defaults to 100 requests a minute and 10 concurrent per key (8). No 429 or retry guidance found (0). No SLA in the terms (0). The REST API and MCP server are both live, not 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.

## 5. Payments & pricing, 35 out of 100, up to 8.1 more on the total

Why it scored 35: No x402, MPP or L402 (0). Public pricing, 2 per cent of sales, or $20 a month for stores under $1,000 in monthly sales, which is per-sale rather than per-call (15). Test mode is free with no card (20). A person signs up in the browser (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.

## 6. Transparency & trust, 65 out of 100, up to 3.1 more on the total

Made of editorial 39, provenance 90.

Why it scored 65: Closed service with published terms (15). Privacy is a section of the terms, last updated 14 March 2022, linking a DPA PDF but giving no retention periods or postal address (10). The additive-only change policy is stated, with no deprecation notices found (10). Payment gateways (Stripe, PayPal, Paymill) and advertising networks are named, with no hosting provider or subprocessor list (4).

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):

- security.txt: not found (0 of 10)

## 7. Maintenance & community, 68 out of 100, up to 2.8 more on the total

Why it scored 68: Release notes on 24 September 2026 (30). Six entries since 3 July, 13 and 28 July, 26 August, and 9, 21 and 24 September (20). Public release notes and a support forum the status page monitors (12). No official API SDK, and the MCP server isn't in the official registry (3). The MCP source isn't public, so its CI can't be seen (3).

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.

- Whether REST list endpoints take limit and offset, and what the error body looks like
- unchecked: whether Duda's security programme covers Snipcart
- Whether the MCP server source is public anywhere. The docs mention an included Dockerfile but give no repository

## Weaknesses

- No server-side cart or checkout. Orders only come from the browser widget
- One full-access key per mode, with no OAuth, scopes or read-only keys
- Refund and archive tools have no documented confirmation or annotations
- No OpenAPI, llms.txt, security.txt or disclosure contact
- The status page doesn't check the API path or the MCP endpoint

## 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 agent for back-office jobs (orders, refunds, discounts, stock, abandoned carts), not for placing orders
- Start with a test-mode key (ST_ prefix) before switching to live (SL_)
- Send the key in X-Snipcart-Api-Key. OAuth-only clients can't connect
- Stay under 100 MCP requests a minute and 10 in flight per key
- Ignore unknown response fields. Snipcart adds fields without a new version

## What the review panel asked for

- A server-side order endpoint
- Document the error body
- read-only API keys
- 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.