Vouched

# Fix list: Vouched

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/vouched, the October 2026 research run, assessed 14 October 2026. Grade C, 56.4 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 Vouched: 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, 40 out of 100, up to 10.5 more on the total

Why it scored 40: Three key types, private for backend calls, public for user-facing capture and signature for webhooks. Only one of each is active, and recreating a key invalidates the old one at once. Separate key sets per group. No scopes (18 of 30). The public key can only submit jobs from capture SDKs, and dashboard access supports SAML single sign-on. No read-only API key, and Delete Job needs no confirmation (8 of 20). Responses carry text extracted from identity documents, with no injection guidance (3 of 15). The dashboard lists jobs with billable and review state. No API audit log found (5 of 15). The security page names penetration tests and vulnerability scans and says certifications are available on request. The DPA refers to SOC 2 or ISO 27001 reports from Vouched or its sub-processors. security.txt returns 404 and no bug bounty was found (6 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. Reliability, 50 out of 100, up to 10 more on the total

Why it scored 50: Read with the hosted lines. status.vouched.id is a Statuspage with API, Management Portal and JS Plugin components (20). Five incidents between 20 July and 1 October 2026. On 1 October rejection rates rose because of ID data extraction on the API and JS Plugin from 11:45 to 12:55 Pacific, labelled major. AML screening errors on 20 July (6 minutes) were also labelled major, and AML latency on 1 August and SSN and DOB API latency on 21 July were minor. An iOS 27 camera issue opened on 14 September has no resolution date (10). The rate-limit page says all endpoints share one limit and a 429 is returned, with no number (3 of 15). Exponential backoff is advised for 429. No Retry-After or idempotency key was found (7 of 15). No SLA found (0). The API is generally available (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.

## 3. Payments & pricing, 30 out of 100, up to 8.8 more on the total

Why it scored 30: Read with the hosted rubric. No x402, MPP or L402 (0). The pricing page publishes Self Starter at $300 a month plus $0.75 a transaction, or $3,000 a year plus $0.70, and Essential at $300 a month plus $1.50 a transaction (20). A 14-day free trial is advertised. We couldn't confirm whether it needs a card (10 of 20). Sign-up is a browser form at app.vouched.id (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.

## 4. Agent ergonomics, 66 out of 100, up to 5.5 more on the total

Why it scored 66: Find Jobs takes `fields`, `withPhotos`, `withPhotoUrls` and `includeResults`, so responses can drop images and results (20). `page`, `pageSize`, sorting and about 40 filters by status, dates, names, ID type and billable state (20). A typed error envelope with types such as `FaceMatchError` and `AuthenticationError` (15 of 20). No idempotency key, and each submitted job is a new, billable job (5 of 20). No server-side SDK. Example repositories in Python, Java, Node.js and React, plus a JS plugin and mobile SDKs for capture (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.

## 5. Maintenance & community, 60 out of 100, up to 3.5 more on the total

Why it scored 60: Release notes dated 28 August 2026, 47 days ago (20). Entries on 20 July, 4 August, 14 August and 28 August (20). A closed service with release notes and support by email (9 of 15). No server SDK. @vouched.id/vouched-react-native 1.5.3 dates from 2 February 2026 (7 of 15). Example repositories exist. CI wasn't checked (4 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, 81 out of 100, up to 3.1 more on the total

Why it scored 81: Each reference page embeds an OpenAPI 3 fragment of the Vouched API, version 0.13.13, with US and EU servers and the sandbox endpoints described. No standalone spec file was found (20 of 25). llms.txt and a Markdown copy of each page (10). Descriptions say how to use each endpoint, for example that the DOB check is synchronous and shouldn't be polled and that TIN verification has no test mode (15 of 20). Typed schemas with an enumerated list of error types (12 of 15). Error types with explanations, a rejection reasons page and Try It examples (12 of 15). Dated release notes and a shutdown date of 31 January 2027 announced for the standalone AML endpoint. The API itself is unversioned in the path (12 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, 74 out of 100, up to 2.3 more on the total

Made of editorial 72, provenance 76.

Why it scored 74: Closed service under published Customer Terms of Service, a public DPA and a legal changelog listing each change by date (18 of 30). The biometric notice (updated 12 February 2026) says biometric data is deleted once its purpose is met or within 3 years of the last interaction. The privacy statement has the same date, and EU accounts store data in the EU while processing runs in the US (22 of 30). The standalone AML endpoint carries a shutdown date of 31 January 2027 in the reference (14 of 20). The DPA's Annex III names sub-processors with locations, and the legal changelog records additions such as Anthropic, Vercel and Zilliz on 16 September 2026 (18 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: vouched.id, registered 2018-11-26 (7 years) (11 of 15)
- Terms of service: read, states 5 of the 7 things a reader expects, and has 3 clauses that cost points (2.3 of 10)
- Privacy policy: read, states 8 of the 8 things a reader expects, and has 1 clause that costs points (8 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.

- Whether the 14-day trial asks for a card. The pricing page doesn't say and we didn't sign up
- The numeric rate limit. The docs say only that all endpoints share one limit
- Vouched also sells Know Your Agent (kya.vouched.id), which identifies AI agents, with its own docs and pricing. It may fit another category and wasn't graded here
- The OpenAPI fragment's info block carries an Apache 2.0 licence, which doesn't match the proprietary service terms
- Vouched Identity, Inc. was named Woolly Labs, Inc. until 9 April 2025, per the legal changelog

## Weaknesses

- Rate limits are stated without a number
- No idempotency key, and each submitted job is billable
- No server-side SDK, only example repositories and capture SDKs
- Webhook signatures use HMAC-SHA1
- No security.txt or bug bounty, and certifications only on request

## 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.

- Use the private key in `X-API-Key` against verify.vouched.id or verify.eu.vouched.id, matching the account's region
- Check Find Jobs before resubmitting. There is no idempotency key and each job is billed
- Pass `withPhotos=false` and select `fields` on Find Jobs to keep responses small
- In a test account, use the name test pass for a clean result and any other name for a failure
- Back off on 429. All endpoints share one limit and no figure is published

## 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.