The Weather Company Data APIs

# Fix list: The Weather Company Data APIs

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/weather-company, the October 2026 research run, assessed 8 October 2026. Grade D, 52.6 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 The Weather Company Data APIs: 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, 20 out of 100, up to 10 more on the total

Why it scored 20: No x402, MPP or L402 (0). The Standard package price is public at $500 a month for 1 million calls on an annual plan. Enterprise plans, add-on packages and overage rates are by contract (10 of 20). A 30-day trial at 50,000 calls a day is free, but it is requested by form and limited to enterprise customers. The form did not load for us, so whether it asks for a card is unchecked, and we gave half (10 of 20). A person requests the trial and sales provisions the key (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, 48 out of 100, up to 9.1 more on the total

Why it scored 48: A plain API key whose endpoints are set by the customer's package. It is accepted only in the query string, so we deducted 10. Revocation and rotation are not documented, and the best-practices page suggests a separate key per use case (10 of 30). The API is read-only (17 of 20). Alert text comes from national agencies and US alert summaries are AI-generated, with no guidance on handling that text (10 of 15). History on Demand has a usage endpoint for key consumption. The customer portal sits behind a login and was not read (3 of 15). weather.com publishes a valid security.txt that expires on 31 December 2026, and the site footer has a security incident contact. A Vanta trust centre exists but is drawn by script and was not read. No bug bounty was found (8 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. Agent ergonomics, 54 out of 100, up to 7.5 more on the total

Why it scored 54: Response size is controlled by choosing a duration endpoint, by the `products` field selection and compact mode on History on Demand, and by aggregation, which is capped at 10 products and 1 MB. There is no general field selection (14 of 25). Only two APIs paginate, Alert Headlines and History on Demand (10 of 20). Errors are JSON with a code and message, such as `CDN-0004` for a missing key, which we observed on an unauthenticated request. Authorisation failures and exceeded limits share 401 (11 of 20). All documented operations are GET requests, so retries are safe (15 of 20). Every v3 call needs a location plus `units`, `language` and `format`, gzip is required, and no official SDK was found (4 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.

## 4. Maintenance & community, 36 out of 100, up to 5.6 more on the total

Why it scored 36: The History on Demand Direct reference records a specification change on 14 September 2026, 24 days before the check, and the documentation sitemap shows pages edited up to 5 October 2026 (30). We found one dated changelog entry in 42 API references sampled, short of three in 90 days (0). Support is by email and a ServiceNow customer portal, and the status page is updated during incidents. No public community channel was found (6 of 15). No official SDK was found (0). No package to assess (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. Reliability, 73 out of 100, up to 5.4 more on the total

Why it scored 73: Status page at theweathercompanyapis.statuspage.io with 16 components (20). Its incident feed shows nine incidents from 10 July to 8 October 2026, all rated minor or none, the longest a degraded Air Quality Global API from 15 to 17 August (20 of 30). Trial limits are published at 100 requests a minute and 50,000 a day, and paid limits are a monthly cap set by contract (15). No 429 is documented, an exceeded limit returns 401, and guidance is limited to spreading requests and honouring Cache-Control (3 of 15). The product page states a 99.95 per cent uptime SLA, with no SLA document published (5 of 10). The v1, v2 and v3 APIs are in production, although the documentation site is labelled beta (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.

## 6. Schema & documentation, 67 out of 100, up to 5.4 more on the total

Why it scored 67: 168 API reference sections are generated from OpenAPI documents (version 3.2.0 in the page data), and 11 Postman collections can be downloaded, but no standalone OpenAPI file was found (18 of 25). No llms.txt (404) and no Markdown copies (0). Overviews state sources, coverage, attribution and behaviour such as the 3 pm daypart change (16 of 20). Parameters carry enums, patterns and required flags (13 of 15). Each operation has an example response, 13 documented status codes and code samples in seven languages, though the error guide says messages may vary by system (12 of 15). Paths are versioned and each API reference has a changelog section, with one dated entry in the 42 we sampled and no central changelog (8 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.

## 7. Transparency & trust, 49 out of 100, up to 4.5 more on the total

Made of editorial 20, provenance 77.

Why it scored 49: A closed service. The website terms of use, updated 16 April 2026, say they do not apply to the business data APIs and refer to separate terms that we did not find published (5 of 30). The privacy policy, effective 30 April 2026, covers business contact data collected through developer.weather.com and says customer-managed personal data is used as business agreements specify. Retention is stated as as long as necessary, and no data processing agreement was found (10 of 30). No deprecation policy or dated deprecation notice was found (0). The policy says data is processed in the United States and other jurisdictions. No sub-processor list was read, since the trust centre is drawn by script (5 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):

- Terms of service: not found (0 of 10)
- Privacy policy: published, but our reader couldn't read it (7 of 10)
- 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 trial request form at wsi.my.site.com/trial, which is drawn by script and did not load, so whether it asks for a card and which terms it links are unknown
- unchecked: the trust centre at trust.weathercompany.com, drawn by script, so certifications, sub-processors and documents were not read
- unchecked: the API customer portal at weather.service-now.com, behind a login, so key rotation, usage views and any terms shown there were not read
- The terms that govern the data APIs were not found on the pricing, trial or documentation pages, so `provenance.terms` is left out
- The 99.95 per cent uptime SLA is a figure on the product page. No SLA document was found
- Changelog sections were read on 42 of 168 API references. The other 126 may hold dated entries
- Overage rates, add-on package prices and Enterprise prices are by contract and not published
- Whether a downloadable OpenAPI file exists. The reference pages embed the documents but no file link was found
- The lead said public docs and a free trial, which is right, but the trial is limited to enterprise customers and is not self-serve

## Weaknesses

- No self-serve signup. The trial is requested through a form, is limited to enterprise customers, and the Buy now button opens a contact form.
- The API key is accepted only as the `apiKey` query parameter, so it appears in every request URL. No header option is documented.
- The website terms of use say they do not apply to the data APIs and point to separate terms, which we did not find published.
- Exceeding a rate limit returns 401, the same status as a missing key. No 429, Retry-After or backoff guidance is documented.
- No llms.txt, no downloadable OpenAPI file, no official SDK and no MCP server were found. Only one dated changelog entry appeared in 42 API references sampled.

## 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 `units`, `language` and `format=json` with a location on every v3 call, plus `Accept-Encoding: gzip`, which the usage guide marks as required.
- Keep the key out of logs and client-side code, because it travels in the query string as `apiKey`.
- Treat a 401 as either a bad key, an endpoint outside the key's package or an exceeded limit, and treat a 204 as no data for the query.
- Each forecast duration (`3day` to `15day`) is a separate entitlement. Request only durations the contract covers.
- Use `/v3/aggcommon` to combine up to 10 products in one request. Each product and each location still counts as one call.

## 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.