Veryfi API + MCP by Veryfi

# Fix list: Veryfi API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/veryfi, the October 2026 research run, assessed 1 October 2026. Grade C, 55.4 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 Veryfi API + MCP: 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: Every request carries CLIENT-ID and an apikey USERNAME:API_KEY header, and requests are signed with HMAC-SHA256 using the client secret, valid for 30 minutes. Keys can be created, removed or reset through the partner API. Scoped Bearer keys come from the 30 September check and aren't on the authentication page (20 of 30). Some actions are admin-only, no read-only key found (5 of 20). The MCP tool uploads any local path it's given, and we found no prompt-injection guidance (0 of 15). The document list shows past submissions, no audit log found (5 of 15). The pricing page claims SOC 2 Type 2, and security contact is cso@veryfi.com. No security.txt or bug bounty found (10 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, 55 out of 100, up to 9 more on the total

Why it scored 55: Better Stack status page with API, API Portal and Lens SDK Repository components, all marked not monitored, plus an incident history (15 of 20). An 'API went down' incident resolved on 29 September with no duration or explanation. On 1 October document processing was degraded for about 7 hours with some failed requests, and a second incident, still open at the 22:26 UTC update, says the API was returning incomplete extraction results for a large portion of requests. Nothing earlier is listed. Several majors (0). 60 requests a second on POST documents, 5 on the document list, 10 a minute for repeated identical failing requests (15). 429 with a Retry-After header in seconds, and an Idempotency-Key on uploads per the 30 September check (15). SLA options on Growth and Enterprise, none published (0). GA (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. Schema & documentation, 50 out of 100, up to 8.1 more on the total

Why it scored 50: llms.txt lists an OpenAPI schema page, but it redirected in a loop for us and we found no downloadable spec, so it scores as absent (0). llms.txt (10). Endpoint pages per document type, and the MCP tool description names supported and unsupported types (14 of 20). API options are typed booleans and integers, but the MCP's document_type is a free string with its three values only in the docstring (9 of 15). An error table with 12 cases from 400 to 503 (12 of 15). Versioned v8 path, no public changelog (5 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.

## 4. Payments & pricing, 40 out of 100, up to 7.5 more on the total

Why it scored 40: No x402, MPP or L402 (0). Per-document prices public, $0.08 a receipt to $0.25 a bank statement or cheque (20). 100 documents a month free with no card (20). A person signs up 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.

## 5. Agent ergonomics, 75 out of 100, up to 4.1 more on the total

Why it scored 75: The MCP server has one tool, and API responses grow only when you ask for bounding boxes or confidence details (20 of 25). max_pages_to_process, boost_mode, opt-in bounding boxes and confidence, and a paged document list (14 of 20). Twelve documented errors with a meaning each (14 of 20). Idempotency-Key on uploads per the 30 September check, and no annotations on the MCP tool (12 of 20). One required input, a file or URL, and SDKs in Python and Node.js among others (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.

## 6. Transparency & trust, 60 out of 100, up to 3.5 more on the total

Made of editorial 40, provenance 80.

Why it scored 60: Closed service under published terms, SDKs and MCP server MIT (15). The privacy policy says submitted data trains Veryfi's own non-generative models, with an opt-out through the business agreement or product settings, and gives no retention period beyond keeping data while you use the service (10 of 30). No deprecation policy or dated notices found (0 of 20). Published subprocessor list and AWS hosting named (15 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):

- Changelog: not found (0 of 10)
- security.txt: not found (0 of 10)

## 7. Maintenance & community, 78 out of 100, up to 1.9 more on the total

Why it scored 78: Node.js SDK v1.5.2 tagged on 2026-09-15, 16 days ago (30). Node.js tagged v1.4.8 (three tags), v1.5.0, v1.5.0.1, v1.5.1 and v1.5.2 since 4 August (20). No public changelog, and the MCP server's last commit was 2025-09-26. Issue replies not sampled (5 of 15). Python SDK 5.1.0 (May 2026) and Node.js 1.5.2 are current (15). Both SDK repositories run test workflows. The MCP server has tests but no CI (8 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.

- The Idempotency-Key and 504 billing guidance come from the 30 September check of the process-a-document page. Our fetch of that page didn't surface them
- unchecked: the OpenAPI schema page listed in llms.txt, which redirected in a loop
- unchecked: how the 1 October incomplete-extraction incident ended and how long the 29 September outage lasted
- unchecked: scoped Bearer keys, which the listing describes but the authentication page doesn't mention

## Weaknesses

- API outage on 29 September and degraded, incomplete extraction on 1 October
- Submitted documents train Veryfi's models unless opted out by agreement
- $500 a month minimum once past 100 free documents
- MCP server has one tool, no package and no commits since 2025-09-26
- No downloadable OpenAPI spec and no public changelog

## 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.

- Always send an `Idempotency-Key` header so a retry after a 504 doesn't bill twice
- Wait for the seconds in `Retry-After` on a 429; identical failing requests are capped at 10 a minute
- Set the `CLIENT-ID` header on every call
- Use the dedicated endpoints for bank statements, cheques and tax forms, since the documents endpoint handles receipts, invoices and purchase orders
- Set `max_pages_to_process` for long PDFs, since one transaction covers 15 pages

## What the review panel asked for

- Make document_type an enum
- Body on 504 errors
- working OpenAPI link

## 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.