# Fix list: Companies House API From Anchor Terminal's listing at https://www.anchorterminal.com/tools/companies-house, the October 2026 research run, assessed 1 October 2026. Grade D, 49.8 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 Companies House API: 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, 38 out of 100, up to 12.4 more on the total Why it scored 38: No public status page found for the API (0). No incident history to read (5). 600 requests per five minutes per key, published in the rate-limiting guide (15). The guide says every request for the rest of the five-minute window gets a 429, and applications that keep exceeding the limit can be banned without notice. No Retry-After header documented (8 of 15). No SLA, and the developer guidelines state no availability commitment (0). 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. ## 2. Security & auth, 45 out of 100, up to 9.6 more on the total Why it scored 45: The key goes in the Basic auth header, never the URL, and the developer guidelines say keys can be restricted by IP address and domain, regenerated and deleted. No permission scopes, since the public data API is read-only (25 of 30). Read-only register data (15 of 20). Company names, officer names and addresses are filed by the public and come back verbatim, with no guidance on treating them as untrusted (5 of 15). No request log or usage view found (0 of 15). No security.txt on api.company-information.service.gov.uk (401) or find-and-update.company-information.service.gov.uk (404), and no reporting process in the developer guidelines (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. ## 3. Payments & pricing, 40 out of 100, up to 7.5 more on the total Why it scored 40: No x402, MPP or L402 (0). Free, which is published (20). Free with no card (20). A person has to create a Companies House account and a key 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. ## 4. Maintenance & community, 25 out of 100, up to 6.6 more on the total Why it scored 25: The last shipped resource change on the forum was the PSC notifications resource on 27 April (157 days, 10 by the letter). A specification change was announced on 29 September and the public api-enumerations repository merged changes on 27 August and 11 September, so we gave 20 (20). One forum notice in the last 90 days (0). Staff post change notices, but developer questions about rate limits from July had no reply per the 26 September check (5 of 15). No official SDK (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. ## 5. Schema & documentation, 60 out of 100, up to 6.5 more on the total Why it scored 60: Swagger 2.0 root spec, 'Companies House Public Data API' 1.0.0, with about 30 paths pointing to per-resource spec files (25). No llms.txt (0). Descriptions are one line per parameter, for example 'The term being searched for', with nothing on when to use an endpoint (10 of 20). Typed parameters with required flags, but filters such as `restrictions` are space-separated strings rather than enums (10 of 15). The search reference shows no example response and documents only 200 and 401. Error strings live in the public api-enumerations repository (5 of 15). Unversioned paths, with dated change notices on the developer forum (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. ## 6. Agent ergonomics, 67 out of 100, up to 5.4 more on the total Why it scored 67: `items_per_page` sizes lists, no field selection (15 of 25). `items_per_page`, `start_index` and `restrictions` on search, so paging and filtering are there (18 of 20). Thirteen error keys such as `company-profile-not-found` are enumerated in public YAML, and 429 is documented (12 of 20). Read-only GETs (15 of 20). Search needs only `q`. No official SDK (7 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, 74 out of 100, up to 2.3 more on the total Made of editorial 67, provenance 80. Why it scored 74: Closed government service. The developer guidelines set no conditions on reuse, and the personal information charter says commercial organisations build products on register data (15). The charter, updated 7 September 2026, sets retention (live companies indefinitely, dissolved companies 20 years before transfer to the public records office, online records now kept permanently) and names a DPO. It doesn't cover developer account data (22 of 30). Dated change notices on the forum, such as removal of officer occupation on 16 October 2025, but no written deprecation policy (15 of 20). Processors listed by category, with cloud in the UK or EU/EEA and the rest UK-based (15 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): - Status page: 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. - Whether any status page or service availability record exists for the API - Whether the 29 September specification change affects the public data API or only filing - unchecked: whether developer forum questions from July 2026 have been answered since the 26 September check ## Weaknesses - A person has to create the account and key - 600 requests per five minutes per key, and the whole window returns 429 once you go over - No status page, SLA, llms.txt or official SDK - No example responses in the reference, and only 200 and 401 documented on search - No security.txt or vulnerability reporting route found ## 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 the key as the Basic auth username with an empty password. `curl -u KEY:` works - Search with `/search/companies?q=` and page with `items_per_page` and `start_index`, then fetch `/company/{number}` - Pad company numbers to 8 characters with leading zeros - Stop on the first 429 and wait out the five-minute window, since every call until it resets also fails - Map filing and error codes to text with the public api-enumerations YAML rather than guessing ## What the review panel asked for - a versioned path or changelog - a status page - example responses ## 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.