YNAB

# Fix list: YNAB

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/ynab, the October 2026 research run, assessed 14 October 2026. Grade B, 65.1 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 YNAB: 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, 30 out of 100, up to 8.8 more on the total

Why it scored 30: No x402, MPP or L402 (0). Public plan prices, $14.99 a month or $109 a year, with the API included at no extra charge (10). 34-day free trial with no card when signing up on ynab.com (20). A person has to sign up in a browser and create a token or OAuth app in Developer Settings (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.

## 2. Security & auth, 51 out of 100, up to 8.6 more on the total

Why it scored 51: OAuth authorisation code grant with PKCE, state, 2-hour access tokens and refresh tokens, with one read-only scope; the implicit grant is still offered, and personal access tokens never expire and carry full access, though each is revocable. Tokens travel only in the Authorization header (22 of 30). The read-only scope returns 403 on writes, but personal access tokens have no read-only option and deletes need no confirmation (10 of 20). Responses include payee names and memos imported from banks; no guidance on treating them as untrusted (5 of 15). No per-call log or audit trail for API use found (0). security.txt with Bugcrowd and security@ynab.com but no Expires line, a public Bugcrowd bounty, and SOC 2 and ISO 27001 claimed only for the AWS infrastructure beneath Heroku (14 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.

## 3. Agent ergonomics, 71 out of 100, up to 4.7 more on the total

Why it scored 71: Specific single-resource endpoints, since_date and until_date, a type filter (`uncategorized`, `unapproved`), and delta requests on nine resources; no field selection (17 of 25). No pagination on lists; date filters and delta requests stand in for it (12 of 20). Errors carry id, name and detail, with 403 split into five documented causes an agent can act on (17 of 20). Reads are safe to repeat and import_id prevents duplicate transactions, with 409 on conflicts and duplicate_import_ids in responses; no idempotency key for other writes (10 of 20). The last-used plan alias cuts a call, few required parameters, and official SDKs for JavaScript, Python and Ruby (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. Schema & documentation, 77 out of 100, up to 3.7 more on the total

Why it scored 77: Public OpenAPI 3.1.1 file, version 1.87.0, 44 operations (25). No llms.txt or Markdown docs for the API; api.ynab.com/llms.txt answers 401 and www.ynab.com/llms.txt describes the app (0). Tag and parameter descriptions say what each resource is and when to use the last-used and default plan aliases, and the docs say to request the most specific resource; little when-not-to-use guidance (14 of 20). Typed parameters with 15 enums, maxLength and required fields, few loose objects (12 of 15). An error table with ids such as 403.1 subscription_lapsed and 403.4 data_limit_reached, sample responses in the docs, few examples in the spec (11 of 15). Versioned spec and a dated changelog from v1.68.0 to v1.87.0 (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. Reliability, 82 out of 100, up to 3.6 more on the total

Why it scored 82: Statuspage at ynabstatus.com with a Public API component and incident history back to 2024 (20). No incident of any kind from 16 July to 14 October 2026; the last one touching the Public API was intermittent loading on 18 November 2025, about 3 hours (30). Rate limit of 200 requests an hour per access token, rolling window, documented (15). 429 too_many_requests is documented with "wait awhile and try again", but there's no Retry-After and the X-Rate-Limit header was removed in v1.73.0; import_id on created transactions matches retries instead of duplicating them (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.

## 6. Maintenance & community, 62 out of 100, up to 3.3 more on the total

Why it scored 62: Last API change v1.87.0 on 17 September 2026 (30). In the last 90 days only v1.87.0 and ynab Python 4.4.0 on 12 August 2026, two dated releases (0). Closed service with a dated changelog and email support at api@ynab.com that says replies may take up to a week; on the JavaScript SDK maintainers merge their own pull requests within days, but an issue opened on 1 August and a community pull request of 23 August have no reply (10 of 15). Three official SDKs, regenerated from the spec; the JavaScript SDK's 4.5.0 of 1 July 2026 predates v1.87.0 (12 of 15). Build and Test CI passing on main on 8 October 2026, Dependabot and Socket scans (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.

## 7. Transparency & trust, 75 out of 100, up to 2.2 more on the total

Made of editorial 57, provenance 92.

Why it scored 75: Closed service with API terms, general terms and a privacy policy; SDKs under Apache-2.0 (15). The privacy policy, effective 20 April 2026, gives retention periods (account data up to 24 months after a subscription or trial ends, support conversations up to 3 years, workshop recordings 21 days) and agrees with the security page on deletion; no DPA or subprocessor list found (20 of 30). Deprecated fields such as goal_target_month and debt_original_balance are dated in the changelog, and the old domain and /budgets paths still work; no written deprecation policy (12 of 20). Data is processed in the US with Standard Contractual Clauses for UK and EEA transfers, hosting on Heroku and AWS and the aggregators Plaid and MX are named, other subprocessors only by category (10 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: read, states 5 of the 7 things a reader expects, and has 3 clauses that cost points (2.3 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: whether Developer Settings shows any per-token usage or last-used date, which the docs don't describe.
- unchecked: whether YNAB holds its own SOC 2 or ISO 27001 report; the security page names only AWS's.
- The JavaScript SDK repository shows a pull request bumping 4.4.0 to 4.5.0 on 19 August 2026, while npm dates 4.5.0 to 1 July 2026; the npm date is used.

## Weaknesses

- Each access token is limited to 200 requests an hour in a rolling window, and 429 responses carry no Retry-After
- Personal access tokens don't expire and can't be limited to reading
- No list pagination, so a full transaction list depends on date filters and delta requests
- Getting access needs a person to sign up and create a token or OAuth app in the web app
- No llms.txt or Markdown version of the API docs; the site's llms.txt is a product description

## 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 last-used in place of plan_id until you have listed plans with GET /v1/plans
- Store server_knowledge and send it back as last_knowledge_of_server to stay inside 200 requests an hour
- Read and write amounts in milliunits, or read the _currency fields added in v1.82.0
- Set import_id on transactions you create so a retried POST is matched instead of duplicated
- Request scope=read-only on OAuth when the task only reads the budget

## 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.