# Fix list: WooCommerce API + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/woocommerce, the October 2026 research run, assessed 1 October 2026. Grade BB, 73 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 WooCommerce 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, 55 out of 100, up to 7.9 more on the total Why it scored 55: REST keys are revocable and set to read, write or read_write per key, and the MCP runs as a WordPress user with an Application Password. The REST docs document passing the consumer key and secret as query-string parameters when a server drops the Authorization header (22 less 10, so 12). Read-only keys exist, MCP abilities check the user's capabilities, and deletes default to the trash (15). The MCP docs warn that order and customer tools expose personal data, but nothing on prompt injection from reviews, notes or product text (5). Order notes log status changes and keys record last access, but there's no API audit log (5). SECURITY.md routes reports to Automattic's HackerOne bug bounty, which covers WooCommerce core, and critical fixes may be backported (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. ## 2. Payments & pricing, 60 out of 100, up to 5 more on the total Why it scored 60: No x402, MPP or L402 in core (0). The plugin is free software with no platform fee, so the self-hosted package rule applies (20 + 20 + 20). Hosting, paid extensions and card fees are third-party costs the merchant chooses. 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. Reliability, 80 out of 100, up to 4 more on the total Why it scored 80: Graded with the self-hosted package checklist, since every store runs on its owner's WordPress host and Woo runs no hosted API. Official plugin on wordpress.org, requiring PHP 7.4 and WordPress 7.0 (20). CI workflow on trunk, the latest 30 runs all green (25). About 1,300 open issues, with recent bugs such as an 11.1.0 release candidate showing $0 flat-rate shipping as "Free!" in emails and a database connection bug (10). Monthly major.minor releases rather than strict semver, with workflows that flag REST API and backwards-compatibility changes for review (10). Stable 11.x (15). The Store API's optional limiter documents RateLimit headers including RateLimit-Retry-After. 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. Schema & documentation, 77 out of 100, up to 3.7 more on the total Why it scored 77: No OpenAPI file. Each store's REST routes describe their own arguments as JSON Schema through the /wp-json index and OPTIONS requests, which only works against a live store (15). llms.txt on developer.woocommerce.com per the 30 September check (10). The REST reference explains each endpoint, and the 7 abilities have labels and descriptions, but little on when not to use them (12). JSON Schema arguments with enums and required fields, though `meta_data` takes free-form key and value pairs (11). Examples in curl, Node.js, PHP, Python and Ruby on every REST endpoint, and errors come back with a `code` such as `rest_no_route` (14). Versioned namespaces (/wc/v3, /wc/store/v1), a public changelog, and REST changes flagged by a workflow on each pull request (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. ## 5. Agent ergonomics, 83 out of 100, up to 2.8 more on the total Why it scored 83: WordPress's `_fields` parameter trims REST responses, and the MCP has 7 abilities (22). `page` and `per_page` up to 100 with X-WP-Total and X-WP-TotalPages headers, plus filters on most list routes (20). Errors carry a `code`, `message` and `data.status`, and the Store API documents its status codes (16). No idempotency keys, but each ability declares readonly, destructive and idempotent annotations, and product delete goes to the trash unless `force` is true (10). Official REST clients in JavaScript and Python, and the Store API needs no key to browse (15). 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. ## 6. Transparency & trust, 76 out of 100, up to 2.1 more on the total Made of editorial 86, provenance 65. Why it scored 76: GPL-3.0 (30). Automattic's privacy policy, updated 11 December 2025, covers Woo services and names the WooCommerce usage tracker, gives about 30 days for server logs, but links no subprocessor list or DPA (18). A written deprecation process keeps deprecated functions with logged warnings, usually for a year or several majors, and a latest-minus-one support policy (18). Usage tracking is opt-in (the woocommerce_allow_tracking setting defaults to no) and the settings page explains what it sends (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. Provenance checks not met in full (half of this category, computed from checked facts): - Endpoint on the vendor's domain: is not on woocommerce.com (0 of 15) - Status page: not found (0 of 10) - 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: 11.1.2 on 22 September 2026, with 11.2.0-beta.2 on 28 September (30). Six stable releases since 3 July, 10.9.4, 11.0.0, 11.0.1, 11.1.0, 11.1.1 and 11.1.2 (20). About 1,300 open issues, labelled by area and type, but a large backlog for the team's size (12). Official JavaScript and Python REST clients exist. The MCP isn't in the official registry, and we didn't check client release dates (10). CI, PHPStan and nightly builds on trunk (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. - When the MCP integration leaves developer preview - Whether the MCP adapter passes the abilities' readonly and destructive flags to clients as readOnlyHint and destructiveHint - unchecked: release dates of the official JavaScript and Python REST clients ## Weaknesses - Uptime, speed and security depend on each store's host and plugins. No vendor status page - MCP is a developer preview behind the mcp_integration flag, with 7 abilities - REST docs allow the consumer key and secret in the query string - Store API rate limiting is off by default - No OpenAPI file, so the contract only comes from a live 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. - Create a REST key with read permission only for reporting tasks, and send it in the Authorization header, never the URL - Get a Cart-Token with GET /wp-json/wc/store/v1/cart and send it on every cart and checkout call instead of a nonce - Add `_fields=id,name,price` to REST calls to cut response size - Page with per_page up to 100 and stop at X-WP-TotalPages - Product delete only trashes unless you pass force true, so check the trash before assuming it's gone ## What the review panel asked for - MCP out of preview - A published OpenAPI file - drop query-string auth - a dedicated MCP role ## 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.