TrueLayer by TrueLayer

# Fix list: TrueLayer

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/truelayer, the October 2026 research run, assessed 1 October 2026. Grade B, 62.4 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 TrueLayer: 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, 10 out of 100, up to 11.3 more on the total

Why it scored 10: No x402, MPP or L402 (0). No prices on the site or in the docs; truelayer.com/pricing returned 404 in the 30 September check (0). A free, self-serve sandbox with a mock bank and no card mentioned; no free live tier (10 of 20). A person signs up in the Console (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, 66 out of 100, up to 6 more on the total

Why it scored 66: OAuth 2.0 from a Console client id and secret, with client_credentials tokens scoped to data or payments, and payments also signed with an EC secp521r1 key whose public half sits in the Console (27 of 30). Each connection asks the user for named scopes on a TrueLayer-hosted page, one_time access avoids a standing consent, and payments can't be sent without the signing key (15 of 20). Returns bank records with merchant-written descriptions; no guidance on treating them as untrusted (7 of 15). llms.txt lists a debug ID endpoint, and no operator request log was found (3 of 15). A disclosure programme at security@truelayer.com with a PGP key, a paid bug bounty on Intigriti, and SECURITY.md in the open-source repos, but security.txt expired on 6 May 2026 and still hadn't been renewed on 1 October; no certifications found on the pages we read (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. Reliability, 71 out of 100, up to 5.8 more on the total

Why it scored 71: Statuspage at status.truelayer.com with components split by product, bank and region (20). From 3 July to 1 October the feed lists 25 incidents, all minor or no impact, nearly all payment settlement delays at banking partners in EUR, GBP and PLN. The broadest were failed requests at the edge gateway on 28 August and degraded edge performance on 17 September; none named the Data API (20 of 30). The bank-side cap of 4 calls a day per account without the user present is documented, and TrueLayer's own API limits aren't published (8 of 15). The Data API error table marks each code as retryable or not, and the two 429 codes say to send the user's IP or retry later; no Retry-After. Payments have a guide to signed, idempotent requests (13 of 15). No SLA found (0). Data and Payments APIs 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.

## 4. Maintenance & community, 38 out of 100, up to 5.4 more on the total

Why it scored 38: Newest release found is truelayer-signing java-v0.3.0 on 25 June 2026, 98 days ago; truelayer-java 17.6.0 shipped on 15 May 2026 (10). No releases or changelog entries in the last 90 days; the changelog's newest entry is 23 April 2026 (0). Closed service with a monthly changelog that went quiet after April; GitHub issue replies weren't sampled because the GitHub API wasn't open to us (8 of 15). truelayer-dotnet's newest tag is 2.0.0-beta4 from November 2025 (10 of 15). The signing repo runs CI per language plus CodeQL, with Dependabot bumps on 20 August 2026 (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.

## 5. Agent ergonomics, 73 out of 100, up to 4.4 more on the total

Why it scored 73: Transactions take date ranges, and Data v3 runs transaction requests asynchronously with a webhook when ready (15 of 25). Date filters; no page-size or cursor control confirmed (12 of 20). 23 documented Data API error codes, each marked retryable or not with a handling note (20). Reads are safe to repeat and payment creation is idempotent with signed requests (16 of 20). Official Java and .NET SDKs and signing libraries in nine languages, but OAuth plus EC request signing for payments is a lot of setup, and recurring access is the default (10 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, 66 out of 100, up to 3 more on the total

Made of editorial 37, provenance 95.

Why it scored 66: Closed service. End-user terms updated 12 May 2026 are public; the developer contract is agreed in the Console and isn't published. Signing libraries are Apache-2.0 or MIT (12 of 30). End-user terms keep data 7 years after last use per the 30 September check; no DPA or subprocessor list on the legal index (12 of 30). The versioning page says TrueLayer doesn't ship breaking changes but gives no notice periods, and we found no dated deprecation notices (8 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). TrueLayer Limited is FCA-authorised under 901096 and TrueLayer (Ireland) Limited by the Central Bank of Ireland under C433487, per the 30 September check (+5).

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):

- security.txt: published but past its Expires date (5 of 10)

## 7. Schema & documentation, 89 out of 100, up to 1.8 more on the total

Why it scored 89: OpenAPI files per API under docs.truelayer.com/openapi/, per the 30 September check (25). llms.txt with about 280 entries and a Markdown twin of each docs page (10). Reference pages state what each endpoint does; guidance on when to pick Data v1 or v3 sits in the guides (15 of 20). Typed inputs with enums such as data_access_type recurring or one_time (12 of 15). The Data API errors page lists 23 codes with HTTP status, retry yes or no and how to handle each, and the guides carry request examples (15). A versioning page and a monthly changelog, but the newest entry is 23 April 2026 (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.

## 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 Data API v3 will cover the EEA, and when; we found no dated plan
- unchecked: whether the Console shows a per-request log to operators
- unchecked: TrueLayer's own API rate limits, beyond the banks' caps
- unchecked: GitHub issue responsiveness on the SDK repositories (the GitHub API wasn't available to us)

## Weaknesses

- No public pricing anywhere on the site or in the docs
- Data API v3 is UK only; Europe runs on Data API v1 with a different flow
- security.txt expired on 6 May 2026 and hadn't been renewed by 1 October
- No changelog entry since 23 April 2026 and no SDK release since 25 June 2026
- TrueLayer's own rate limits aren't published, only the banks' 4-a-day cap

## 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 auth.truelayer-sandbox.com and api.truelayer-sandbox.com with a separate sandbox client; live credentials don't work there
- Send the user's IP when they're present, or a bank allows 4 calls a day per account
- Check the retry column of the Data API error table before retrying; codes marked No need the user or a config fix
- Set data_access_type to one_time for a single read and skip the 90-day reauthorisation
- Append .md to any docs URL to get the page as Markdown

## What the review panel asked for

- dated data v3 plan
- a resumed monthly changelog
- renew security.txt
- operator request 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.