Medusa API + MCP by Medusa

# Fix list: Medusa API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/medusa, the October 2026 research run, assessed 1 October 2026. Grade B, 63.6 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 Medusa 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, 40 out of 100, up to 10.5 more on the total

Why it scored 40: Publishable keys scoped to sales channels for the Store API, revocable secret API keys or user JWTs for the Admin API. A secret key has full admin reach (20). Publishable keys limit what a shopping agent sees, and role-based access is behind a feature flag per the 2.20.1 notes (8). The API returns merchant- and shopper-entered text with no prompt-injection guidance found (5). No audit log found (0). SECURITY.md with security@medusajs.com and a 3-business-day response promise, but no security.txt, no bounty, no SOC 2 found, and no published GitHub advisories even though 2.20.1 shipped a security fix to field filtering (7).

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. Reliability, 55 out of 100, up to 9 more on the total

Why it scored 55: Graded on Medusa Cloud, the hosted option. Atlassian Statuspage at status.medusajs.com with an incident feed (20). Four incidents since 18 August, all short. New deployments failing on 18 August and on 30 September (about 50 minutes), the Cloud dashboard down for 8 minutes on 16 September with customer apps unaffected, and 12 minutes of degraded availability in the EU central region the same day (20). No API rate limits published, only monthly edge-request quotas per plan (0). No 429 or backoff guidance found (0). A 99.99% uptime guarantee is listed for Enterprise on the pricing page, with no SLA document published (5). Generally available (10). Self-hosted stores have no vendor status at all.

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. Payments & pricing, 50 out of 100, up to 6.3 more on the total

Why it scored 50: No x402, MPP or L402 (0). Medusa Cloud plan prices start from $29, $99 and $299 a month with per-unit overage ($0.30 per 1M edge requests, $20 per 100,000 search requests), all public, but each plan is a floor price (15). The MIT core is free to self-host with no card (20). An agent can install and run the core locally with `npx create-medusa-app` and 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.

## 4. Agent ergonomics, 72 out of 100, up to 4.6 more on the total

Why it scored 72: Responses can be trimmed with `fields`, and store routes cap relation depth at three since 2.20.0 (22). `limit`, `offset`, `order` and per-field filters on list routes (20). Errors carry `type`, `code` and `message`, documented in the spec (15). A 409 example tells the caller to retry with an Idempotency-Key, but no such header is documented on any route (5). Few required parameters and a typed JS SDK, but no second official language (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, 81 out of 100, up to 3.1 more on the total

Why it scored 81: OpenAPI 3.0 files for the Store API (68 paths, 78 operations at 2.21.2) and the Admin API live in the repo, with a frozen copy per release (25). llms.txt with about 200 entries (10). Reference descriptions state what each route does but rarely when not to use it (12). Typed query and body parameters with required fields, though `fields` takes a free-form expression and filters accept `$and` and `$or` (11). Error responses are documented per route (400, 401, 404, 409, 422, 500) with typed error objects, and the reference carries JS SDK and curl examples (13). Release notes have a breaking changes section, but breaking changes ship in minor 2.x releases, with breaking sections in 2.16.0, 2.17.0, 2.18.0, 2.19.0 and 2.20.0 and even the 2.17.2 patch (10).

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. Transparency & trust, 73 out of 100, up to 2.4 more on the total

Made of editorial 71, provenance 75.

Why it scored 73: MIT for the repository except Enterprise Edition files, which a separate proprietary licence covers (25). Privacy policy updated 7 September 2026 with a linked DPA, naming AWS, Vercel, PostHog, Google Analytics, OpenAI and Anthropic, but retention is "as long as necessary" with no periods (18). No written deprecation policy. Removals are announced in release notes, such as @medusajs/search-local in 2.20.0 (10). CLI telemetry is on by default, announced with a printed notice, and turned off with `medusa telemetry --disable` or MEDUSA_DISABLE_TELEMETRY (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):

- Endpoint on the vendor's domain:  is not on medusajs.com (0 of 15)
- security.txt: not found (0 of 10)

## 7. Maintenance & community, 93 out of 100, up to 0.6 more on the total

Why it scored 93: v2.21.2 on 28 September 2026 (30). Seven releases since 3 July, from v2.18.0 to v2.21.2 (20). 68 open issues, the newest labelled within a day of opening, with triage and stale-bot workflows (20). Current official JS SDK released with each version, and the docs MCP is in the official registry as com.medusajs/medusa-mcp (15). CI pipeline on every push to develop and every pull request, plus Dependabot triage. We didn't see run results (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.

- The privacy policy describes a Medusa Cloud MCP connector whose tool results can include customer names, addresses and orders, but we found no docs for it (docs.medusajs.com/cloud/mcp returns 404)
- unchecked: whether Medusa Cloud enforces per-second API rate limits
- Whether the security fix in 2.20.1 will get a public advisory

## Weaknesses

- The official MCP server is docs-only and limited to Cloud accounts
- Breaking changes ship in minor releases, listed in 2.16.0, 2.17.0, 2.18.0, 2.19.0 and 2.20.0
- No rate limits, retry guidance or documented idempotency header
- No public security advisories, security.txt or audit log
- Some files sit under a proprietary Enterprise Edition licence

## 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.

- Send x-publishable-api-key on every /store call. It decides which sales channels and products the agent sees
- Ask for only the fields you need with `fields`. Store routes reject relations nested more than three deep since 2.20.0
- Read the store's regions before creating a cart, since prices and shipping options depend on region
- Place the order with POST /store/carts/{id}/complete after shipping and payment sessions are set
- Read the release notes before upgrading a minor version. Breaking changes land there

## What the review panel asked for

- Store-data MCP tools
- Document the Idempotency-Key header
- released role-based access
- public security advisories

## 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.