Zus Health

# Fix list: Zus Health

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/zus-health, the October 2026 research run, assessed 14 October 2026. Grade C, 56.6 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 Zus Health: 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, 5 out of 100, up to 11.9 more on the total

Why it scored 5: Read with the hosted rubric. No x402, MPP or L402 (0). No published prices (0). A developer sandbox is requested by Google Form, limited to test data, with no price stated (5 of 20). Zus provisions accounts and users (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.

## 2. Security & auth, 49 out of 100, up to 8.9 more on the total

Why it scored 49: OAuth 2.0 with one-hour tokens, machine-to-machine App Clients managed in the app, token exchange from the customer's identity provider and a proxy-token endpoint now limited to a dedicated role (22 of 30). Managed roles such as Builder Admin and Builder Data Integration, with no read-only API role confirmed (12 of 20). The ZAP returns documents and data from outside organisations with no prompt-injection guidance (3 of 15). AuditEvent is a supported resource and the Builder Security Policy asks builders to keep audit logs, with no operator-facing API log documented (7 of 15). No named certification, an annual third-party audit summary on request, no security.txt or bug bounty (5 of 20).

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.

## 3. Reliability, 66 out of 100, up to 6.8 more on the total

Why it scored 66: Read with the hosted lines. status.zusapi.com on StatusPal with components and history (20). Between 16 July and 14 October 2026 it lists major incidents on the athenahealth embedded app (27 July), ZusHooks delays of up to two hours (4 August), risk gap calculations (5 August) and the embedded app across EHRs (13 August), with FHIR API errors on 24 August marked minor. Several majors, none on the FHIR API itself (5 of 30). Rate limits with numbers for FHIR, tokens and Patient History (15). 429 is documented with no Retry-After or backoff guidance, while conditional writes by identifier and `Zus-If-Match` make retries safe (8 of 15). A published SLA of 99.5 per cent with credits (10). FHIR REST is generally available and GraphQL is beta (8 of 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.

## 4. Agent ergonomics, 67 out of 100, up to 5.4 more on the total

Why it scored 67: `_count` up to 500, and GraphQL selects only the fields requested, though GraphQL is beta (20 of 25). FHIR search parameters across resources and lastUpdated ordering (18 of 20). Error responses are not described beyond 429 (10 of 20). Conditional create by identifier and `Zus-If-Match` version checks, no idempotency keys (14 of 20). No official SDK, a Postman collection only (5 of 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.

## 5. Schema & documentation, 77 out of 100, up to 3.7 more on the total

Why it scored 77: Each reference page carries an OpenAPI 3.0.3 fragment with enums and required fields, with no single specification file found (18 of 25). llms.txt and Markdown pages (10). Guides explain the ZAP, Patient History jobs and when to subscribe or query once (13 of 20). Typed inputs with enums on Auth Service and Patient History operations, FHIR search parameters listed (12 of 15). A Postman collection and Loom walkthroughs, with little on error bodies (9 of 15). A dated changelog with about ten entries since 29 July 2026 (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. Transparency & trust, 59 out of 100, up to 3.6 more on the total

Made of editorial 46, provenance 71.

Why it scored 59: Closed service with published Builder Terms, Developer Sandbox Terms, BAA and SLA (15 of 30). The terms forbid de-identifying Patient Data for sale but let Zus use and sell System Data. The privacy policy covers the website only, with no retention periods (15 of 30). The terms promise reasonable efforts at 60 days' notice for changes that aren't backwards-compatible, and the changelog announces dated changes in advance (14 of 20). No sub-processor list or data location found (2 of 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 zushealth.com (0 of 15)
- Privacy policy: read, states 3 of the 8 things a reader expects (6.3 of 10)
- security.txt: not found (0 of 10)

## 7. Maintenance & community, 64 out of 100, up to 3.2 more on the total

Why it scored 64: The Builder Data Integration role change took effect on 14 October 2026 and the last dated entry is 21 September 2026 (30). About ten dated changelog entries since 29 July 2026 (20). A public changelog, a weekly product email and a Zendesk support form. We did not test support (11 of 15). No official SDK was found (0 of 15). A maintained Postman workspace (3 of 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.

- Whether the developer sandbox is free and how quickly a form request is answered is not stated
- unchecked: whether Zus holds SOC 2 or HITRUST, since no certification was named on the pages read
- No error response format was found in the documentation read

## Weaknesses

- No public prices, and the sandbox is requested through a Google Form
- Four major incidents on the status page between 27 July and 13 August 2026
- No named security certification, security.txt or bug bounty
- The GraphQL API is beta and no official SDK exists

## 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.

- Cache the access token for its hour. More than 200 token requests an hour per App Client returns 429
- Request Patient History at most once per patient per 24 hours, and poll the job status endpoint
- Use conditional create by identifier so a retried write doesn't duplicate a resource
- Send `Zus-If-Match` with the resource's ETag on PUT and PATCH
- Set `_count` up to 500 on searches, since the default page is 10

## 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.