Worklio

# Fix list: Worklio

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/worklio, the October 2026 research run, assessed 9 October 2026. Grade E, 38.6 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 Worklio: 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, 25 out of 100, up to 15 more on the total

Why it scored 25: Read with the hosted rubric, for embedded-payroll partner access. status.worklio.com exists and asks for a password, so there is no public status page (0) and no readable incident history (5). No rate limits were found in the docs index or the guides read (0). No 429 or backoff guidance and no idempotency keys. The reference says starting a scheduled payroll twice returns the same run, and that bonus, off-cycle, void and termination starts are not idempotent (5 of 15). The security page says the Service Level Agreement targets 99.9 per cent availability, with no SLA document or credits published (5 of 10). The API is in production use and not marked beta (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.

## 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). Retail list prices per person per month are public, $10 for Full-Service Payroll, and the page says they are not a quote and that the partner's rate card sits in its agreement (10 of 20). The sandbox is open to any registered developer per the docs. The registration page was not read because its host disallows crawlers, so the card question is open (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, 44 out of 100, up to 9.1 more on the total

Why it scored 44: No field selection, and the pagination guide says most `/wep` endpoints return their full result set on every call (8 of 25). The `/api/public` endpoints take `limit`, `skip`, a filter language with 18 single-field operators and multi-field sorting, with a page token that expires after 60 seconds (12 of 20). Errors share one envelope with a code and per-field validation errors, but the Run Payroll guide tells callers to read an HTTP 500 with an untranslated message as the cue to finalise, and `errorCode` is null in that example (9 of 20). No idempotency keys. Scheduled payroll starts are idempotent, runs can step back or be discarded, and updates use JSON Merge Patch (9 of 20). Creating a company needs four fields and an employee five. No public SDK (6 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. Security & auth, 48 out of 100, up to 9.1 more on the total

Why it scored 48: Bearer JWTs with one scope, `api`, lasting 24 hours. The sandbox uses the password grant with a client secret printed in the docs and shared by all sandbox users, and the browser flow uses `response_type` `id_token token`. Production credentials are issued by Worklio, and no rotation or revocation procedure was found (14 of 30). Four user levels are enforced per operation and an Employee sees only its own data. No read-only role was found. A run must be locked and finalised in separate calls (11 of 20). Responses carry text entered by employers and workers, with no injection guidance, and the employee create response echoes the full Social Security number (3 of 15). The security page says changes by administrators, employees and clients are logged in an audit trail. No general audit endpoint was found in the index (8 of 15). SOC 2 Type 2, ISO 27001, ISO 27018 and ISO 9001 are claimed, with outside penetration testing. No security.txt, disclosure policy or bug bounty (12 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.

## 5. Maintenance & community, 25 out of 100, up to 6.6 more on the total

Why it scored 25: The last dated API change is the pair of changelog entries of 30 June 2026, 101 days before the check (10 of 30). No changelog entry falls in the last 90 days. The docs sitemap shows 25 pages updated between 3 September and 8 October 2026, which we counted as half (10 of 20). A closed service with a help centre and a contact form, no public issue tracker or community (5 of 15). No public SDK or package (0 of 15, 0 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.

## 6. Schema & documentation, 71 out of 100, up to 4.7 more on the total

Why it scored 71: Each of the 853 reference pages embeds an OpenAPI 3.0.4 fragment with schemas and the bearer scheme. No single downloadable spec was found (20 of 25). llms.txt and a Markdown copy of every page (10). 821 of 853 operations carry a description, and many state which user levels may call them and in which run state (14 of 20). Inputs are typed with formats and required flags. Enums are integers whose meanings sit in description text (10 of 15). The quick-start guides give curl, Node.js and Python examples with 400 responses, while the two reference pages sampled document only a 200 (7 of 15). An `api-version` header and a changelog with two entries, both dated 30 June 2026 (10 of 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.

## 7. Transparency & trust, 48 out of 100, up to 4.6 more on the total

Made of editorial 28, provenance 67.

Why it scored 48: Closed service. The only public terms are Terms of Use last updated 21 December 2014, written for a small-business HR site and limited to personal, non-commercial use. The partner agreement isn't public (8 of 30). The privacy policy is hosted on iubenda at a path its robots.txt disallows, so it was not read. The security page gives seven days of nightly backups, 35 days of point-in-time restore and storage in the United States. No DPA was found (8 of 30). The changelog notes replaced routes and a retired preview API, and the docs mark the v1 embedded screens as legacy with a migration guide. No removal dates or policy (5 of 20). Microsoft Azure and United States locations are named, and the docs mention Plaid and Middesk. No subprocessor list (7 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):

- Terms of service: not found (0 of 10)
- Privacy policy: published, but our reader couldn't read it (7 of 10)
- Status page: not found (0 of 10)
- security.txt: not found (0 of 10)

## Deductions

Each comes off the total. A fixed and documented problem counts for less at the next check.

- 30 June 2026. The changelog entry that announces the reworked Time-Off Requests API says the older `timeoffrequests` routes were replaced by hyphenated routes and tells integrators to update, in the same note and with no earlier notice found. Whether partners were told privately is unknown, so the smallest deduction applies (-3). https://apidocs.worklio.com/changelog/v1-api-updates

## 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 privacy policy. It is hosted at www.iubenda.com/privacy-policy/25719508, a path iubenda's robots.txt disallows
- unchecked: the developer registration page and sandbox dashboard at apiweb.worklio.com, whose robots.txt disallows every path. Whether registration needs a card or approval is not known
- unchecked: the help centre at support.worklio.com, which was not read
- Whether a single OpenAPI file can be downloaded. Only per-page fragments were seen
- Whether the old time-off request routes stopped answering on 30 June 2026 and whether partners had earlier notice
- Rate limits and whether 429 responses carry Retry-After. Nothing was found, and we had no token
- Partner prices, the partner agreement, the SLA text and any DPA or subprocessor list
- How production client credentials are issued, rotated and revoked
- The scope and dates of the SOC 2 and ISO certificates named on the security page
- The legal entity's address and state of incorporation. The footer says Worklio, Inc. and the about page says Worklio LLC was established in 2017

## Weaknesses

- No rate limits, 429 handling or idempotency keys were found in the reviewed documentation
- status.worklio.com asks for a password, so no public incident history exists
- The Run Payroll guide says the `next` call answers HTTP 500 with an untranslated message when a run is ready to finalise
- No public SDK. `@worklio/sdk` and the component library sit in a private repository granted through support
- The public Terms of Use are dated 21 December 2014 and describe a small-business HR site. The partner agreement and production prices aren't public

## 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 `api-version: 2.0` on `/wep` calls. The reference marks the header as required
- Get a token from `POST https://api.worklio.com/connect/token` with the password grant and scope `api`. It lasts 24 hours, so fetch a new one daily
- Run payroll as start, `next` until it answers 500 with "Next step operation is not allowed", then `finalize`. Don't treat that 500 as a failure
- Don't retry bonus, off-cycle, void or termination payroll starts blindly. The reference says those calls are not idempotent
- Most `/wep` list endpoints return the whole result set. Paging, `filter` and `sort` work only under `/api/public`, and a `DataToken` expires after 60 seconds

## 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.