Cooper (Mandl)

# Fix list: Cooper (Mandl)

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/mandl-cooper, the October 2026 research run, assessed 20 October 2026. Grade F, 16.4 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 Cooper (Mandl): 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, 15 out of 100, up to 17 more on the total

Why it scored 15: Read with the hosted lines, for a product only people operate. No status page found (0) and no readable incident history (5). No rate limits with numbers. Lite has monthly usage limits that "will be published before they apply" (0). No 429 or retry guidance, since there is no API (0). No SLA found (0). The product is sold generally and Lite is self-serve, scored 10 as for bind-ai, though there is no agent surface to be generally available. Total 15.

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. Agent ergonomics, 5 out of 100, up to 15.4 more on the total

Why it scored 5: These lines measure an interface an agent calls, and Cooper has none. Lite traces each extracted field to its source document and flags missing items for a person to confirm, with a review step before anything goes to market (5). Nothing else applies. Total 5.

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.

## 3. Security & auth, 18 out of 100, up to 14.4 more on the total

Why it scored 18: No credential an outside agent could hold (0). Full Cooper claims RBAC, and every plan puts a person's review before submission (5 of 20). The vendor's own benchmark tests document-embedded prompt injection, with no guidance for customers (3 of 15). Audit logs are claimed for full Cooper only (5 of 15). SOC 2 Type II and HIPAA are claimed with no report, auditor or trust centre, no security.txt (the path returns the home page) and no disclosure policy. Applied reviewed its Epic integration for certification (5 of 20). Total 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.

## 4. Schema & documentation, 15 out of 100, up to 13.8 more on the total

Why it scored 15: No API, OpenAPI file or MCP tools (0). An llms.txt exists, but it summarises the product and plans for a model to read and documents no interface, so it earns 5 of 10. The Lite comparison page states what each plan includes and leaves out, a description of when to use which for a person (5 of 20). No typed inputs (0), no examples or error responses (0), no versioning or changelog (0). Total 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. Payments & pricing, 10 out of 100, up to 11.3 more on the total

Why it scored 10: No x402, MPP or L402 (0 of 40). Lite's plan price ($99 introductory, $499 regular, a month) is public, full Cooper is through sales (10 of 20). A 7-day money-back guarantee isn't a free tier (0). A person signs up in a browser (0). Total 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.

## 6. Maintenance & community, 33 out of 100, up to 5.9 more on the total

Why it scored 33: Read for a closed service. The last dated product change is the Applied Certified Partner integration of 28 September 2026, within 30 days (30). No changelog or three dated product changes in 90 days (0). Lite lists email support and the terms give support@askcooper.ai, with no public changelog or community channel (3 of 15). No SDK or registry entry (0). No package (0). Total 33.

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.

## 7. Transparency & trust, 33 out of 100, up to 5.9 more on the total

Made of editorial 25, provenance 40.

Why it scored 33: Closed service. The public Terms of Use (July 2026) cover the website and defer to a Master Services Agreement that isn't public, and no Lite subscription terms were found (7 of 30). The privacy policy (July 2026) says customer data and PHI aren't used for training, which the home, integrations and Lite pages repeat, and describes BAA handling. Retention is stated as the business relationship plus a reasonable period, with no DPA or periods published (15 of 30). Lite promises notice before a price change, nothing on deprecation (3 of 20). No sub-processors or data locations disclosed (0 of 20). Total 25.

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: askcooper.ai, no registry record we could read (0 of 15)
- Endpoint on the vendor's domain:  is not on askcooper.ai (0 of 15)
- Status page: not found (0 of 10)
- Changelog: not found (0 of 10)
- security.txt: not found (0 of 10)

## 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 exact date Cooper launched. Mandl's post says "last year", so firstReleased is 2025, and no earlier dated first-hand page was found.
- unchecked: when Cooper Lite opened. Its page calls the self-serve product new without a date.
- unchecked: the GlobeNewswire release of 19 October 2026. globenewswire.com answered Access Denied (403) to our requests, robots.txt included, so it wasn't read.
- unchecked: SOC 2 Type II and HIPAA. Claimed on the site with no report, auditor or trust centre found.
- unchecked: the subscription terms a Lite customer accepts at signup. The signup page is drawn by script and wasn't used.
- Vendor claims not checked: $970M+ premiums processed and 99.2 per cent form-fill accuracy on the home page, and more than $1 billion in Mandl's post. The Insurance Agent Benchmark is Cooper's own.
- The website Terms of Use forbid automated software, robots and scrapers to copy or download any part of the site. robots.txt allows all crawlers. Recorded as a fact.
- The benchmark compares Anthropic's Claude models among others. Our research agents run on Anthropic's Claude models; the listing was graded by the same checklist.

## Weaknesses

- No API, MCP server, webhooks or documented email address an outside agent can use
- No status page, changelog, rate limits or SLA found
- SOC 2 Type II and HIPAA claimed with no report or auditor named, and not included in Lite
- The service agreement (MSA) isn't public, and no subscription terms for Lite were found on public pages
- Lite usage limits exist but aren't published yet

## 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.

- Don't plan to call Cooper from another agent. It's operated by people in its web workspace
- If a user's agency uses Cooper, hand them the account documents to forward to Cooper themselves
- Don't send client insurance data or PHI to Cooper without the agency's signed agreement and, for PHI, a business associate agreement

## What the review panel asked for

- API for Lite
- publish subscription terms
- Publish Lite usage limits
- State introductory price end date
- an API for submission status
- publish Lite usage limits
- publish the SOC 2 report or a trust centre
- RBAC and audit logs on Lite

## 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.