# Fix list: Everee From Anchor Terminal's listing at https://www.anchorterminal.com/tools/everee, the October 2026 research run, assessed 8 October 2026. Grade C, 55.1 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 Everee: 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, 10 out of 100, up to 11.3 more on the total Why it scored 10: Read with the hosted rubric. No x402, MPP or L402 (0). Three pricing models are named, each behind a custom quote. The pricing calculator's defaults of $10 per paid worker a month and $0.75 per payment are the only figures, so partial credit (5 of 20). The pricing page lists a free sandbox, reached through a sales contact (5 of 20). A person books a call to get a company instance before any token exists (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. ## 2. Security & auth, 43 out of 100, up to 10 more on the total Why it scored 43: One API token per company instance, created, rotated and deleted by an administrator in the portal, with no scopes documented (20 of 30). Eight reference fragments declare an OAuth password flow with read and write scopes that the authentication guide doesn't mention, which we didn't count. Payments wait for a payroll admin's approval unless auto-approval is arranged, timesheet corrections are opt-in and browser requests are rejected. No read-only token (12 of 20). Responses carry text entered by workers and employers, with no guidance on untrusted content (3 of 15). A `request_id` on each response. No audit log or per-call log was found in the docs (2 of 15). The technology page says "SOC II Certified" with multi-factor authentication and encryption. No report, security.txt, disclosure policy or bounty found (6 of 20). Total 43. 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. Agent ergonomics, 56 out of 100, up to 7.2 more on the total Why it scored 56: `size` sets a page, default 20, and bulk endpoints take up to 1,000 earnings. No field selection (12 of 25). `page` and `size` on eight list endpoints with `totalPages` and `totalElements`, and filters by worker, payment, paid state, date and lifecycle status (15 of 20). Errors return `errorCode`, `errorMessage`, `path` and `timestamp` with a `request_id` header. The code was the HTTP status on the call we made, and named errors exist only for Timesheets (11 of 20). `externalId` is required on payable items and rejects repeats, and corrections to paid timesheets need `correction-authorized=true`. No general idempotency header (13 of 20). No SDK in any language was found. Every call needs two headers, and embeddable screens cover onboarding and pay history (5 of 15). Total 56. 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. Schema & documentation, 67 out of 100, up to 5.4 more on the total Why it scored 67: Each reference page embeds an OpenAPI 3.0.1 fragment for its operation with request and response schemas, 51 operations in all. No single downloadable file was found (17 of 25). `llms.txt` lists 79 pages, each with a Markdown copy (10). 40 of 51 operations carry a description, and the Timesheets and Payables guides say which API to use for which pay and when not to. Six operations have no summary and one is titled "Copy of" (14 of 20). 36 enums and 60 required lists, with 5 of 268 objects left bare and timestamps as epoch integers (11 of 15). 356 examples and a table of 14 Timesheets errors. 400 is declared on 20 operations, 401 on 8 and 429 on none, and the error envelope isn't described (9 of 15). Paths are versioned as v1 and v2. No changelog exists, and three migration guides stand in for one (6 of 15). Total 67. 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. Maintenance & community, 46 out of 100, up to 4.7 more on the total Why it scored 46: The newest dated change is a reference guide updated on 6 October 2026 (30). There is no dated changelog. 15 docs pages carry update dates between 27 July and 6 October 2026, which we counted as half (10 of 20). Closed service with support@everee.com and a help centre our reader couldn't draw. No public changelog, issue tracker or community (4 of 15). No official SDK. The docs give embed sample code for five platforms (2 of 15). No public package or repository to judge (0 of 10). Total 46. 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. ## 6. Transparency & trust, 56 out of 100, up to 3.9 more on the total Made of editorial 39, provenance 73. Why it scored 56: Editorial half only. Closed service. The Terms and Conditions and the Payroll & Payment Service Terms, both last updated 18 June 2025, are public and name APIs. Partner pricing terms are not (15 of 30). The privacy policy of 3 January 2025 gives no retention periods, and no DPA was found (9 of 30). Everee states that breaking changes get a timeline of months or years, published one with dates (November 2025 to 1 April 2026) and marks five items deprecated. No standing policy page (12 of 20). The policy says data may be stored in the United States or elsewhere, and The Bancorp Bank is named for the pay card. No sub-processor list found (3 of 20). Total 39. 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): - Terms of service: read, states 7 of the 7 things a reader expects, and has 3 clauses that cost points (4 of 10) - Privacy policy: read, states 6 of the 8 things a reader expects (8.5 of 10) - Changelog: not found (0 of 10) - security.txt: not found (0 of 10) ## 7. Reliability, 87 out of 100, up to 2.6 more on the total Why it scored 87: Read with the hosted rubric, on the Integration API of a company instance. status.everee.com on Better Stack lists API, Web App, Mobile App and Time Clock Terminal with 90 days of history (20). From 11 July to 8 October 2026 the API component logged 730 seconds of downtime on three days in July, and the two posted incidents were three-minute outages of the Time Clock Terminal. Reports are automatic monitor entries (30). The limit is published as 200 operations per 5 seconds (15). The docs describe 429, exponential backoff with jitter and four `RateLimit-*` headers including the reset time. A repeated payable `externalId` is rejected. No `Idempotency-Key` or `Retry-After` is documented (12 of 15). The terms make no representation about uptime and no SLA was found (0). The API carries no beta label (10). Total 87. 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. ## 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 help centre at help.everee.com, which is drawn by script and showed our reader no content, so any release notes or security articles there were unread - Whether a sandbox has its own host and whether it can be had without a sales call. The docs name only https://api.everee.com - Whether the OAuth password flow with read and write scopes declared in eight reference fragments is live. The authentication guide documents only the Basic token - Whether webhooks are signed and how failed deliveries are retried. Neither is documented - The scope and date of the SOC 2 report claimed on the technology page - Real prices. The calculator's $10 and $0.75 are editable defaults labelled base prices, not a quote - Whether a single OpenAPI file can be downloaded. We found only per-page fragments - How Everee's ban on agents, monitoring and benchmarking in its Terms and Conditions applies to API use under a signed agreement - The docs site's 404 page carries a line for AI agents pointing to `llms.txt`. It is a navigation hint from the docs host and nothing was acted on ## Weaknesses - No preview or approval endpoint was found. Payments are approved by a payroll admin in the Everee portal, or automatically if Everee sets that up. - The Terms and Conditions forbid access through any agent or tool other than Everee's software or a web browser, and forbid monitoring availability or benchmarking. - A company instance starts with a demo call. No self-serve signup, public sandbox host or plan price was found, only calculator defaults of $10 per paid worker and $0.75 per payment. - No SDK, single OpenAPI file or API changelog was found, and `developer.everee.com/changelog` returns 404. - Tokens carry no scopes or read-only form in the docs, and no audit log or webhook signature was found. ## 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 two headers on every call, `authorization: basic ` and `x-everee-tenant-id`. Base64-encode a token that starts with `sk_` first. - Derive each payable's `externalId` from stable data, never a timestamp or UUID, so a retried create is rejected instead of paying twice. - For contractors, call POST `/integration/v1/payables/payment-request` after all payable items are sent and before admins approve. Without it contractors aren't paid. - Send hourly wages through the Timesheets API, not Payables, and assign `workLocationId` so tax is worked out for the right jurisdiction. - Don't expect the API to move money alone. Tell the user a payroll admin must approve in the portal unless auto-approval is enabled, and read Everee's terms on automated access first. ## 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.