# Fix list: Codat From Anchor Terminal's listing at https://www.anchorterminal.com/tools/codat, the October 2026 research run, assessed 8 October 2026. Grade B, 64.3 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 Codat: 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 price is published. The pricing page returns 404 and the MSA leaves the platform fee and the per-company unit fee to an order form (0). The docs describe a free trial of up to 50 companies for 365 days and a sandbox excluded from billing, but the docs say to get in touch to create an account, so half credit (10). Access starts with a person contacting Codat (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, 49 out of 100, up to 8.9 more on the total Why it scored 49: Plain API keys in a Basic header, up to 10 per client, named, revocable in the Portal or through the API. No scopes and no documented expiry (20). No read-only key and no confirmation step for writes or deletes. Portal users have roles, and only Administrator and Developer roles see keys (4). The API returns ledger text written by third parties, such as invoice descriptions and supplier names, and no injection guidance was found (3). Read and write history per company and data type in the Portal and through the data history and push endpoints. No log of calls per API key was found (7). Annual SOC 2 Type II and ISO 27001 audits, a yearly penetration test, a private bug bounty and a disclosure form on codat.io/security. No security.txt. The trust centre page did not render for us (15). 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, 80 out of 100, up to 4 more on the total Why it scored 80: Graded on the hosted REST API at api.codat.io. Statuspage at status.codat.io with components per product and per integration (20). In the 90 days to 8 October 2026 the page shows two complete outages of the API and Portal, 14 minutes on 24 July and 12 minutes of errors on 27 July, intermittent Xero failures from 22 to 29 July, and errors on some integrations and sync services for about two hours on 24 August. No single outage of the core API reached an hour, so we scored it as one major (10). Limits published with numbers, 1,000 requests a day times one plus the active connected companies, 10 concurrent per company and 1,000 a minute per IP (15). 429 with Retry-After and X-Rate-Limit headers, and an Idempotency-Key header on POST and PATCH (15). The standard MSA pays service credits below 99 per cent monthly uptime (10). 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. Schema & documentation, 77 out of 100, up to 3.7 more on the total Why it scored 77: Public OpenAPI 3 specs for every API in codatio/oas, in JSON and YAML (25). docs.codat.io/llms.txt returns 404. The docs source is Markdown in a public repository, which is not the same as serving it to agents (0). Operation descriptions are long and state prerequisites, useful queries and traps, for example that data must be refreshed before a list call (16). Typed schemas with enums, but filters go through a free-text `query` string and the required fields of a write differ by accounting package and have to be fetched from an options endpoint (11). Response examples per integration on most operations and a documented status code table with sample error bodies (13). Dated changelog at docs.codat.io/updates and a change policy. The API has no version in the path or a header (12). 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, 81 out of 100, up to 3.1 more on the total Why it scored 81: `pageSize` from 1 to 5,000 with a default of 100, and a `query` filter that cuts results. No field selection found (15). Page and pageSize paging with `_links`, a query language, `orderBy` and modifiedDate filters. Bill Pay uses continuation tokens (20). Errors carry statusCode, service, error, correlationId, canBeRetried and detailedErrorCode with a validation object, though the error text is a string an agent has to read (17). Idempotency-Key on POST and PATCH with a 90-minute cache and documented behaviour after a 429. PUT and DELETE are outside the documented scheme (18). Maintained SDKs for TypeScript, Python and C#, one package per product. Writes need a model lookup per integration and most complete asynchronously (11). 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, 71 out of 100, up to 2.5 more on the total Made of editorial 59, provenance 82. Why it scored 71: Closed service with a published Master Services Agreement, versioned and dated, naming Codat Limited and its company number (15). The MSA has a data processing schedule and deletes company data five business days after termination. The privacy notice of April 2025 is written mainly for website visitors and gives general retention wording, with six years for customer records (16). A change policy with at least three months' notice of breaking changes, a deprecation calendar, quarterly emails, defined lifecycle states and dated notices (20). The privacy notice names Microsoft Azure in the UK as a sub-processor and the MSA promises 10 days' notice of changes. No fuller list or choice of data location was found (8). 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: codat.io, registered 2016-10-17 (9 years) (11 of 15) - Terms of service: read, states 6 of the 7 things a reader expects, and has 1 clause that costs points (7.1 of 10) - Privacy policy: read, states 7 of the 8 things a reader expects (9.3 of 10) - security.txt: not found (0 of 10) ## 7. Maintenance & community, 75 out of 100, up to 2.2 more on the total Why it scored 75: Latest changelog entry on 1 October 2026 (30). Seven dated entries since 3 August 2026 (20). A dated changelog, a Zendesk help centre and a support address. No public issue tracker for the service was reviewed (10). TypeScript, Python and C# SDKs were last published between April and June 2026. The Java and Go SDKs were archived in April and May 2026 with a month's notice (10). The specs repository runs lint in CI and was last changed on 4 August 2026 (5). 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: whether app.codat.io/signup still opens a free account without sales contact. The page is a JavaScript app we could not read, and the docs say to get in touch - unchecked: the trust centre at trust.codat.io, which did not render, so the sub-processor list and certificates there were not read - unchecked: the official MCP registry for a Codat server. A search returned unrelated results and none was found in Codat's docs - Whether a new client can still buy read access to the full accounting data model outside the Lending product - The enterprise MSA and the Start-up Plan terms were not read in full, and current fees are in order forms only - Idempotency-Key is documented for POST and PATCH, while the Bill Pay spec also lists it on two PUT operations ## Weaknesses - No public price. The pricing page returns 404 and fees are set in an order form - No self-serve signup found. The docs and the site ask new users to get in touch - The general Accounting API spec says it is relevant only to existing clients, and the status page labels it Legacy - API keys have no scopes or read-only mode, and one key reaches every connected company - Two complete API outages in July 2026, of 14 and 12 minutes, and intermittent Xero failures from 22 to 29 July - The Java and Go SDKs were archived in April and May 2026 ## 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. - Send `Authorization: Basic ` to https://api.codat.io. The Portal shows the ready-made header value - Send a new GUID as `Idempotency-Key` on every POST and PATCH, and reuse the same key when retrying after a 429 - Treat writes as asynchronous on most APIs. Keep the push operation key and wait for the `{dataType}.write.successful` or `.unsuccessful` webhook - Call the Get model (options) endpoint for the connection before a create or update, because required fields differ by accounting package - Filter with `query=modifiedDate>...` and keep `pageSize` at 100. The daily quota is 1,000 requests times one plus the number of active connected companies ## 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.