Enable Banking by Enable Banking

# Fix list: Enable Banking

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/enable-banking, the October 2026 research run, assessed 1 October 2026. Grade D, 47.3 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 Enable Banking: 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, 33 out of 100, up to 13.4 more on the total

Why it scored 33: No public status page found. Since August 2026 the Control Panel has an ASPSP status page with ongoing, planned and historic disruptions per bank, behind a login (5 of 20). No readable incident history (5). The FAQ documents the banks' cap of 4 data fetches a day without the user online; Enable Banking's own limits aren't published (8 of 15). A bank refusal comes back as 429 ASPSP_RATE_LIMIT_EXCEEDED, with no Retry-After, backoff or payment idempotency guidance found (5 of 15). No SLA found (0). Generally available; the old api.tilisy.com host is marked deprecated (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, 20 out of 100, up to 10 more on the total

Why it scored 20: No x402, MPP or L402 (0). Volume pricing with a minimum monthly invoice, figures on request (0). The Mock ASPSP and bank sandboxes are free with an account, and restricted mode serves your own whitelisted live accounts before any contract, with no card (20). A person creates the account and registers the application 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. Security & auth, 47 out of 100, up to 9.3 more on the total

Why it scored 47: Each call carries an RS256 JWT signed with the application's private key (kid is the application id, at most 24 hours), so no shared secret crosses the wire; no scopes on the application (25 of 30). Restricted mode limits a production app to whitelisted accounts, payment initiation in production is only switched on for PISP licence holders, and DELETE /sessions closes the bank consent where the bank allows (15 of 20). Returns bank records with merchant-written descriptions; no guidance on treating them as untrusted (7 of 15). No operator request log found (0 of 15). No security.txt per the 30 September check and no disclosure policy, bug bounty or certification found; the FAQ lists none (0 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.

## 4. Schema & documentation, 54 out of 100, up to 7.5 more on the total

Why it scored 54: No OpenAPI file found; the reference documents schemas such as ErrorResponse, and the samples repo has a Postman collection (8 of 25). enablebanking.com/llms.txt returns 404 (0). The reference describes each endpoint and parameter (14 of 20). Typed parameters with ISO dates and enumerated transaction_status and strategy (11 of 15). Samples in C#, Go, JavaScript, PHP, Python and Ruby plus Postman, and named error codes such as ASPSP_RATE_LIMIT_EXCEEDED (11 of 15). A monthly changelog on the blog, newest on 9 September 2026; no API version numbers (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.

## 5. Agent ergonomics, 67 out of 100, up to 5.4 more on the total

Why it scored 67: Transactions filter by date_from, date_to and transaction_status, with a strategy parameter for how they're fetched (20 of 25). continuation_key pagination (20). ErrorResponse with named codes that separate a bank's limit from other failures (14 of 20). Reads are safe to repeat; no idempotency guidance for payments found (8 of 20). No official SDKs, only samples, and a JWT has to be minted before the first call (5 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.

## 6. Transparency & trust, 51 out of 100, up to 4.3 more on the total

Made of editorial 35, provenance 66.

Why it scored 51: Closed service with no public terms of service; the FAQ refers to a contract agreed by email, and the legal pages need JavaScript per the 30 September check. Samples are Apache-2.0 (8 of 30). The FAQ says Enable Banking doesn't store, cache or process account data except to deliver it to the authorised application; no retention periods or readable privacy policy (10 of 30). Dated deprecations in the changelog, such as the UI widgets moving origin with a January 2027 timeline, and api.tilisy.com marked deprecated (14 of 20). No subprocessor list or data location statement found (0). Regulatory standing counts here as an addition to the checklist (+5 for a named regulator with a register number, +3 for a named regulator alone). The home page says Enable Banking is a registered AISP supervised by the Finnish FIN-FSA, per the 30 September check, with no register number we could read (+3).

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: enablebanking.com, registered 2018-04-23 (8 years) (11 of 15)
- Terms of service: not found (0 of 10)
- Status page: not found (0 of 10)
- security.txt: not found (0 of 10)

## 7. Maintenance & community, 67 out of 100, up to 2.9 more on the total

Why it scored 67: Changelog for August 2026 posted on 9 September, adding an ASPSP disruptions view, Swedish BBAN handling and one new bank (30). Changelog posts on 8 July, 12 August and 9 September (20). Closed service with a monthly changelog and email support; GitHub issue replies weren't sampled because the GitHub API wasn't open to us (12 of 15). No official SDKs; the samples repo's last change was a JWT dependency fix on 30 March 2026 (3 of 15). No CI in the samples repo (2 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.

- unchecked: the privacy policy and any terms, which render only with JavaScript
- unchecked: whether the Control Panel shows per-request logs to operators
- unchecked: the claimed 2,700-plus banks in about 30 countries; we didn't recount this run
- Which legal entity and business ID contract with customers; the pages we could read don't say

## Weaknesses

- No public prices and a minimum monthly invoice
- No public status page; bank disruptions sit behind the Control Panel login
- No OpenAPI file, llms.txt or official SDK, only samples
- No public terms, security.txt, disclosure policy or certification found
- No idempotency guidance for payments

## 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.

- Mint one JWT per run with exp under 24 hours; don't reuse a long-lived token across sessions
- Test against the Mock ASPSP first; bank sandboxes fail for reasons that aren't yours
- Pass the bank's maximum_consent_validity as valid_until, usually 180 days, or you'll be back at the bank sooner
- On 429 ASPSP_RATE_LIMIT_EXCEEDED stop until tomorrow; it's the bank's 4-a-day cap
- Follow continuation_key until it's absent to get every transaction

## What the review panel asked for

- version numbers on the api
- a public status page
- publish a security.txt
- per-request operator log

## 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.