ROOK

# Fix list: ROOK

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/rook, the October 2026 research run, assessed 14 October 2026. Grade C, 54.9 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 ROOK: 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, 32 out of 100, up to 11.9 more on the total

Why it scored 32: One client UUID and secret per environment over Basic auth, secret shown once, no scopes, expiry or rotation found (12 of 30). No read-only credential. A revoke endpoint ends a user's connection (5 of 20). Responses are structured health metrics with little free text (10 of 15). No audit log or per-call log found in the reviewed documentation (0 of 15). The site states a HIPAA-aligned programme, BAAs and GDPR processing, and the services terms list AES-256 at rest, TLS 1.2 and MFA. No SOC 2 or ISO 27001, security.txt or bug bounty found (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.

## 2. Payments & pricing, 25 out of 100, up to 9.4 more on the total

Why it scored 25: Read with the hosted rubric. No x402, MPP or L402 (0). Plan prices with user caps and add-on prices are public, with no per-unit price for usage past the cap (10). A Sandbox comes with portal registration and the pricing page says Get started free. We could not see whether a card is asked for (15 of 20). A person registers in a 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.

## 3. Agent ergonomics, 49 out of 100, up to 8.3 more on the total

Why it scored 49: Summaries and per-type event endpoints size responses by date, with no field selection found (12 of 25). A page parameter and date filters on the data endpoints (12 of 20). Errors are JSON with error, exception, path and method, and the WAF answers 403 for missing User-Agent (12 of 20). Mostly reads. No idempotency keys, and dedupe rests on document_version (6 of 20). Few required parameters, but every call needs a User-Agent and there is no server-side SDK (7 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.

## 4. Reliability, 75 out of 100, up to 5 more on the total

Why it scored 75: Read with the hosted lines and scored on the REST API. rook.statuspage.io has components for the API, the connections page and each authorisation source (20). No incident in the 90 days to 14 October 2026. The feed holds seven entries since 2023, the last on 20 October 2025, so the clean record rests on a sparsely used page (30). Typical limits of 60 requests a minute and 10,000 a day are published, varying by plan (12 of 15). No 429 or Retry-After behaviour documented. Dedupe guidance on document_version, and published webhook retries (3 of 15). The services terms cite an SLA page that isn't linked, and pricing lists Basic SLAs on Core with no text found (0). The API carries no beta label (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. Schema & documentation, 74 out of 100, up to 4.2 more on the total

Why it scored 74: OpenAPI 3.0.3 file with 29 operations linked from the Redoc reference (25). llms.txt indexes the site and docs, with no Markdown copies of pages found (6 of 10). Descriptions state what each endpoint returns, and the guides say the API is for occasional queries (12 of 20). Four enums and 20 required lists in the file (6 of 15). 286 examples and responses for 400, 401, 403, 404 and 422 on some operations, with test constants in the description (10 of 15). Versions in the path, spec version 2.0.1, and a dated public changelog (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, 55 out of 100, up to 3.9 more on the total

Made of editorial 52, provenance 58.

Why it scored 55: Closed service with public services terms dated August 2026 (15 of 30). The privacy policy of 28 May 2026 says data is stored in AWS in the United States and names AWS and Google Cloud as core sub-processors. The DPA and BAA are referenced but not public, and no fixed retention periods were found (15 of 30). Terms changes get 30 days' notice, add-ons can be discontinued on reasonable notice, and each SDK LTS release has six months of support (12 of 20). Hosting providers and the US location are named, with no full sub-processor list (10 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):

- Domain age: tryrook.io, no registry record we could read (0 of 15)
- Endpoint on the vendor's domain:  is not on tryrook.io (0 of 15)
- Terms of service: read, states 7 of the 7 things a reader expects, and has 1 clause that costs points (8 of 10)
- security.txt: not found (0 of 10)

## 7. Maintenance & community, 73 out of 100, up to 2.4 more on the total

Why it scored 73: Changelog entry dated 7 October 2026 and capacitor-rook-sdk 4.2.1 published on 8 October (30). Five dated changelog entries between 25 August and 7 October 2026 (20). Closed service with a Canny changelog, email and Intercom support and a Slack community. We could not test response times (10 of 15). Mobile SDKs are current, with no server-side SDK and no entry in the official MCP registry (8 of 15). CI results could not be read (5 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.

- unchecked: whether portal registration asks for a card, and any user cap in Sandbox. The portal sits behind a login
- unchecked: the SLA document the services terms cite as SLAs - ROOK. It isn't linked from the terms or listed in the sitemap
- unchecked: GitHub stars, open issues and CI for RookeriesDevelopment. The GitHub API refused us for rate limits
- unchecked: live API behaviour beyond one unauthenticated Sandbox request, which returned 401 JSON
- The founder's lead gave rookmotion.com, which did not load (expired certificate). ROOK now trades from tryrook.io, and the API lives on rook-connect.com
- The pricing page lists an EHR/EMR API on a waitlist, so clinical records are not available today

## Weaknesses

- Credentials are one client UUID and secret per environment, sent by Basic auth, with no scopes or rotation documented
- Typical limits of 60 requests a minute and 10,000 a day vary by plan, and no 429 or Retry-After behaviour is documented
- No server-side SDK. The official SDKs are mobile libraries for iOS, Android, Flutter, React Native and Capacitor
- The services terms cite an SLA page that isn't linked or published, and no SOC 2 or ISO 27001 report was found
- A WAF blocks requests without a User-Agent header and parameters containing localhost or SQL-like text

## 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 HTTP Basic auth with client_uuid as the username and the secret key as the password, plus a User-Agent header, or the WAF returns 403
- Use https://api.rook-connect.review for Sandbox and https://api.rook-connect.com for production. Each has its own credentials
- Read health data from the data webhook. Use the API only for occasional queries, and stay under 60 requests a minute
- Deduplicate summaries on document_version and datetime. ROOK resends a summary with a higher document_version when it changes
- Call POST /api/v1/user_id/{user_id}/data_sources/revoke_auth to end a connection. Some providers take hours to stop sending data

## 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.