BigCommerce API + MCP by BigCommerce (Commerce.com)

# Fix list: BigCommerce API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/bigcommerce, the October 2026 research run, assessed 1 October 2026. Grade B, 64.5 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 BigCommerce 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, 62 out of 100, up to 7.6 more on the total

Why it scored 62: Atlassian Statuspage at status.bigcommerce.com with API & Webhooks, Checkout & Payment Processing, Storefront and B2B components, and a history feed (20). The feed, read on 2 October, goes back to 6 July and holds about 30 incidents in 90 days, nearly all on a subset of stores or one provider. The longest were catalogue import and export stalled for about 11.5 hours (23 to 24 July), Cybersource payment errors for about 11 hours (15 to 16 July), checkout errors on stores using state or province shipping zones for about 4.6 hours (9 July), availability problems on a subset of stores for about 2.9 hours (10 July), and search degraded on a subset of stores for about 16 hours from 1 October. Elevated HTTP 500s hit storefront and API requests for 15 minutes on 6 July. Nothing took the management API down for an hour, so we count the 10 July availability incident as the one major and weigh the steady run of partial incidents there too (10). Published limits, 450 requests per 30 seconds on Pro and 150 on Plus and Standard, refreshed every 30 seconds (15). A 429 carries X-Rate-Limit-Time-Reset-Ms and the docs advise waiting that long, then backing off exponentially. No idempotency keys for writes found (12). No SLA found (0). REST APIs are generally available, the storefront MCP is beta (5).

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, 40 out of 100, up to 7.5 more on the total

Why it scored 40: No x402, MPP or L402 (0). Plan prices public, Core $39, Growth $105 and Scale $399 a month with GMV caps and 2.0, 1.0 and 0.6 per cent on orders through non-embedded providers, but nothing per call (10). 15-day free trial, and the pricing page says no credit card is needed (20). An agent can shop any store that has switched on the MCP as a guest with no key, but back-office access needs a person to create an API account (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.

## 3. Agent ergonomics, 62 out of 100, up to 6.2 more on the total

Why it scored 62: The B2C storefront MCP reference lists 7 compact, shopping-only tools, and search_products pages with a cursor (23). REST listings take page and limit, with filters such as id:in, type and severity on the store logs endpoint, and the GraphQL Storefront API documents pagination (16). 429 handling is documented, but we found no error-format reference in the docs index (10). No idempotency keys, and the MCP reference documents no tool annotations (0). Guest MCP needs no key. Official API clients for Python, PHP, Ruby and Node, three updated in 2026 and the Python client last in January 2024 (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.

## 4. Schema & documentation, 66 out of 100, up to 5.5 more on the total

Why it scored 66: Reference pages are built from API specs (a 29 September changelog entry corrected twenty of them), but the public spec repo was archived in December 2023 and its successor, bigcommerce/docs, still asked git for credentials on 2 October, so no current spec file was found (10). llms.txt hub linking a developer index of about 500 Markdown pages, plus a docs MCP server (10). Reference descriptions say what each call does, and the MCP tools are guest shopping steps (12). Typed REST parameters in the reference (11). Examples in the reference, but the developer index has no page on error responses (10). Dated changelog with entries almost daily, v2 and v3 REST paths, and a Deprecations and Sunsets page, though it gives no notice period (13).

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.

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

Why it scored 70: API accounts issue a token limited by OAuth scopes chosen at creation and revocable by deleting the account, but tokens never expire and can't be rotated in place (24). Read-only scope variants, and the MCP has no back-office tools, so a guest agent can only shop (16). The MCP returns merchant product content with no prompt-injection guidance found (5). The store logs API (GET /v3/store/systemlogs) keeps storefront events such as order status changes for 365 days, and the control panel keeps staff action logs (a status incident on 8 July names them). No per-call API log found (8). Trust centre lists PCI DSS Level 1 as merchant and service provider, SOC 1, SOC 2 and SOC 3, ISO/IEC 27001:2022 with 27017, 27018 and 27701, and a vulnerability disclosure programme run through Inspectiv. No security.txt per the 30 September check (17).

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.

## 6. Transparency & trust, 78 out of 100, up to 1.9 more on the total

Made of editorial 65, provenance 90.

Why it scored 78: Closed platform with published terms, now on commerce.com, and an open-source Catalyst storefront (15). The trust centre lists a DPA and a subprocessor document. The commerce.com privacy policy wasn't read in either pass (22). A Deprecations and Sunsets page lists deprecated v2 endpoints and three dated sunsets, the last on 3 June 2024, but the current deprecations carry no sunset dates and no notice period is stated (10). Subprocessor document listed and Google Cloud named as the host (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):

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

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

Why it scored 82: Changelog entries on 30 September 2026 (30). Ten entries on 29 and 30 September alone (20). Public changelog and a support centre (12). The storefront MCP isn't in the official registry. Official API clients updated in March 2026 (PHP), May 2026 (Ruby) and August 2026 (Node), while the Python client's last release was 0.23.4 in January 2024 (12). Catalyst repo runs end-to-end tests on main (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: the error response format of the REST management APIs. The developer index has no error page and the system logs reference didn't render its detail
- unchecked: the commerce.com privacy policy and stated retention periods
- The status history feed ended at 23 September when read on 2 October, so the 26 and 27 September and 1 October search incidents rest on the status page as read on 1 October
- No current public API spec. bigcommerce/docs, the stated home of the specs, still asks git for credentials

## Weaknesses

- Storefront MCP is beta, switched on per store, has no back-office tools and documents no tool annotations
- Access tokens never expire and can't be rotated in place
- No current public OpenAPI file and no error-format reference. The old spec repo was archived in December 2023
- About 30 status-page incidents between 6 July and 1 October 2026, the longest about 16 hours of degraded search on a subset of stores
- Rate-limit quota is shared by every app on the store

## 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.

- Give the agent a store-level API account with only the scopes the task needs, and delete it when done
- On a 429, wait X-Rate-Limit-Time-Reset-Ms before retrying
- Expect up to 10 minutes after a store owner enables the MCP before the URL answers
- The MCP stops at a checkout URL. Payment happens in the shopper's browser
- Point a coding agent at the docs MCP at https://docs.bigcommerce.com/_mcp/server

## What the review panel asked for

- Server-side checkout completion
- Expiring tokens
- token expiry and rotation

## 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.