Met Office Weather DataHub (Site Specific) by Met Office

# Fix list: Met Office Weather DataHub (Site Specific)

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/met-office-datahub, the October 2026 research run, assessed 1 October 2026. Grade E, 45.5 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 Met Office Weather DataHub (Site Specific): 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. Schema & documentation, 32 out of 100, up to 11.1 more on the total

Why it scored 32: No OpenAPI or other machine-readable contract found. The API documentation page renders only in a browser and the 30 September check found no spec (0). No llms.txt or Markdown docs (0). The overview explains each product, its sites, timesteps and update cadence, with a parameter glossary (12 of 20). `timesteps` takes hourly, three-hourly or daily, and latitude, longitude and the key are required (10 of 15). Sample data and download code, but the only error documented is the 429 (7 of 15). The path is /v0 and there's no changelog (3 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.

## 2. Reliability, 48 out of 100, up to 10.4 more on the total

Why it scored 48: The hub has a service status page, marked beta, that shows data availability for five atmospheric model feeds. It doesn't cover the site-specific API and keeps no history (10 of 20). No incident record to read (5). Daily call limits published per plan, 360 a day free on Global Spot, and the FAQ says a 429 means the daily limit is spent, resetting at 00:00 UTC (15). The Met Office's own download script waits 10 seconds and retries, but no Retry-After or backoff guidance is documented (8 of 15). No SLA for site-specific plans (0). Global Spot is generally available, and the blended probabilistic forecast lost its beta label in the official utilities on 11 February 2026 (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. Payments & pricing, 30 out of 100, up to 8.8 more on the total

Why it scored 30: No x402, MPP or L402 (0). Plan prices in GBP published without login, but no per-call price (10 of 20). Global Spot free at 360 calls a day, and the pricing page says no payment is required (20). A person registers, creates an application and orders a plan 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. Agent ergonomics, 53 out of 100, up to 7.6 more on the total

Why it scored 53: `excludeParameterMetadata=true` drops the parameter descriptions, and the timestep sets the length. Global Spot returns a fixed parameter set, while the probabilistic forecast lets you pick parameters (15 of 25). No paging or field selection on Global Spot (10 of 20). Only the 429 is documented (8 of 20). Read-only GETs (15 of 20). Three required inputs, no SDK, and Python sample scripts in the MetOffice/weather_datahub_utilities repository (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.

## 5. Maintenance & community, 15 out of 100, up to 7.4 more on the total

Why it scored 15: No dated API change or release note found. The official utilities repository removed the probabilistic forecast's beta flag on 11 February 2026 (232 days) and fixed an atmospheric download option on 22 September 2026. We gave 10 for the active tooling rather than 30, since neither is an API release (10 of 30). No dated API changes in the last 90 days (0). A support ticket form and dpt@metoffice.gov.uk, no public changelog (5 of 15). No SDK or MCP server (0). The utilities repository has no CI (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. Security & auth, 66 out of 100, up to 6 more on the total

Why it scored 66: Keys are issued per application and tied to one product order, sent in an `apikey` header, shown once and resettable, and can't move between applications (24 of 30). Read-only data (15 of 20). Returns forecast numbers only, no untrusted text (10 of 15). The hub tracks API usage against each plan, but we found no per-call log (7 of 15). security.txt on metoffice.gov.uk points to a HackerOne form, per the 30 September check. No certification found for the hub (10 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.

## 7. Transparency & trust, 63 out of 100, up to 3.2 more on the total

Made of editorial 36, provenance 90.

Why it scored 63: Closed service. The FAQ describes a perpetual, worldwide licence to copy, publish, distribute and adapt the data with a credit line, but the full DataHub terms appear only at checkout behind a login (18 of 30). The Met Office privacy policy, updated 3 April 2024, names the controller and a data protection contact, keeps data 'as long as necessary' and doesn't mention DataHub accounts or API usage (12 of 30). No deprecation policy or dated notices found (0). No processors named. Transfers outside the UK or EEA only with safeguards (6 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):

- Changelog: 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: the site-specific API documentation page, which renders only with JavaScript, may hold a specification we couldn't read
- unchecked: the full DataHub terms, shown only at checkout behind a login
- Whether paid or enterprise plans carry an SLA

## Weaknesses

- No OpenAPI, llms.txt, SDK or MCP server
- Only the 429 error is documented, and the path is still /v0
- No changelog, deprecation policy or status coverage for the site-specific API
- Full DataHub terms shown only at checkout behind a login
- Prices only in GBP, and a separate plan for each product

## 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.

- Register an application and subscribe it to the Global Spot plan first. The key is tied to that order and shown once
- Send the key in the apikey header with Accept: application/json, and latitude and longitude as query parameters
- Add excludeParameterMetadata=true to drop the parameter descriptions from every response
- Pick the timestep by need. hourly covers 48 hours, three-hourly 168, daily 7 days, and each call counts against the daily limit
- Stop on a 429. The limit is daily and resets at 00:00 UTC

## What the review panel asked for

- Publish DataHub terms openly
- Add programmatic signup
- publish the API spec
- terms outside the login

## 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.