# Fix list: Salt Edge Account Information From Anchor Terminal's listing at https://www.anchorterminal.com/tools/salt-edge, the October 2026 research run, assessed 1 October 2026. Grade D, 46.9 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 Salt Edge Account Information: 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 published prices; the product page points to a sales form (0). Free Test status with fake providers and bank sandboxes, no card mentioned; no free live tier (10 of 20). A person signs up in the dashboard and Live needs approval (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. Reliability, 52 out of 100, up to 9.6 more on the total Why it scored 52: Status page at saltedgestatus.com with 16 components, the Account Information API, Payments API and Open Banking Gateway among them (20). Only the last fortnight was readable. The history page renders with JavaScript and robots.txt blocks the JSON feed, and what shows is one upstream routing interruption of about five minutes on 29 September and nothing else since 17 September. We scored that 10 of 30 for partial history, not a clean record. Per-second limits published for the reference endpoints, 10 a second on providers, countries, rates and categories and 5 on POST merchants, while parallel connection limits are agreed with a project manager (10 of 15). Going over returns HTTP 406 with RateLimitExceeded rather than 429, with no Retry-After, backoff or idempotency guidance (2 of 15). No SLA found (0). API v6 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. Security & auth, 46 out of 100, up to 9.5 more on the total Why it scored 46: App-id and Secret headers, and Live applications must also sign each call with a private key over Expires-at, method, URL and body, with Expires-at at most an hour ahead; the docs say to regenerate the key and update the public key after a breach. No scopes on the app credential (24 of 30). Consents carry scopes (holder_info, accounts, transactions) and period_days, PUT /consents/{id}/revoke ends one, and Test and Pending apps can't reach real banks (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, /security returns 404, and no disclosure policy, bug bounty or certification found (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, 52 out of 100, up to 7.8 more on the total Why it scored 52: No OpenAPI file found; the quick starts link Postman collections (8 of 25). No llms.txt per the 30 September check (0). The API reference describes each endpoint and its parameters (14 of 20). Parameters are typed with ranges, such as per_page from 100 to 1,000 with a default of 100 (10 of 15). Errors are grouped by layer (API, client configuration, provider, user) with error_class, HTTP code and description, and the quick starts carry examples (13 of 15). Version in the URL with a stated 12-month transition window; no changelog found (7 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. Maintenance & community, 13 out of 100, up to 7.6 more on the total Why it scored 13: No changelog. The newest dated product change found is the blog post of 3 June 2026 launching commercial variable recurring payments in the UK, 120 days ago (10). No dated product changes in the last 90 days; blog posts since July are events, insights and a partner launch (0). Support runs through a project manager, with no public changelog (3 of 15). No official SDKs (0). No package to judge (0). 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. Agent ergonomics, 67 out of 100, up to 5.4 more on the total Why it scored 67: per_page from 100 to 1,000 and filters on account_id, from_date, to_date and pending let a call be sized (20 of 25). from_id cursors with next_id and a ready-made next_page URL (20). error_class and error_message on every error, but the rate limit comes back as 406 instead of 429, which most retry logic won't catch (14 of 20). Reads are safe to repeat; no idempotency guidance for payments (8 of 20). No official SDKs, only sample apps in Java, .NET, PHP, Python and Ruby, and Live calls need request signing (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. ## 7. Transparency & trust, 77 out of 100, up to 2 more on the total Made of editorial 73, provenance 80. Why it scored 77: Closed service with public terms of service (15). The privacy policy, last updated 14 September 2023, keeps backups up to one month after deletion and logs at least five years, and names its processors (20 of 30). The versioning section gives a 12-month window to move off a deprecated version, with no dated notices found (15 of 20). Processors named with countries, Hetzner in Germany and Finland, AWS in Ireland, SendGrid in the US and Yandex for analytics; EU and EEA data stays in the EU, other data may be processed in Canada, the UK or Moldova (18 of 20). 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). Salt Edge Limited is FCA-authorised under 822499 per the 30 September check; the pages we read name no EU authorisation (+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): - Changelog: not found (0 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. - unchecked: status incident history before 17 September 2026 (history page needs JavaScript and the JSON feed is blocked by robots.txt) - unchecked: whether Salt Edge publishes an MCP server or llms.txt this run; the 30 September check found neither - Whether Salt Edge holds ISO 27001 or SOC 2; nothing we read says so - Which entity contracts with EU customers; the pages we read name only the UK subsidiary and the Canadian parent ## Weaknesses - Rate limit exceeded returns HTTP 406 RateLimitExceeded, not 429 - No public pricing; parallel connection limits are negotiated - No official SDKs, OpenAPI file, llms.txt or changelog - No security.txt, security page, disclosure policy or certification found - Status history readable only for the last fortnight; the JSON feed is blocked by robots.txt ## 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. - Treat HTTP 406 with error_class RateLimitExceeded as a rate limit and back off; it isn't a content-negotiation error - Start with fakebank_simple_xf in country XF; it needs no bank sandbox - Sign requests from the start even in Test, so the move to Live doesn't change your client - Follow next_page from the meta block rather than building from_id URLs yourself - Revoke with PUT /api/v6/consents/{consent_id}/revoke when the user is done ## What the review panel asked for - a public changelog - dated deprecation notices - publish a security.txt - scopes on app credentials ## 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.