# Fix list: NOAA National Weather Service API (api.weather.gov) From Anchor Terminal's listing at https://www.anchorterminal.com/tools/nws-api, the October 2026 research run, assessed 1 October 2026. Grade D, 49.9 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 NOAA National Weather Service API (api.weather.gov): 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, 25 out of 100, up to 15 more on the total Why it scored 25: No status page for the API (0). Outages go to NCO Tech Control by email or phone, and the NCEP Senior Duty Meteorologist messages the docs point to are a free-text log with no component history, and none of the messages we could read mentioned the API (5 for no readable history). The rate limit is described as 'not public information' (0). The docs say a throttled request 'may be retried after the limit clears (typically within 5 seconds)', and every call is a GET, but no Retry-After header is documented (10 of 15). No SLA, and no paid tier to carry one (0). The API is the operational NWS service (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, 53 out of 100, up to 8.2 more on the total Why it scored 53: No credential at all. A User-Agent header identifies the caller and the spec says no limits depend on it. We scored this 20, since there's no secret to leak but also nothing to revoke or scope (20 of 30). Read-only public data, no write actions (15 of 20). Alerts and text products are free text, but written by NWS forecasters, the issuing agency (10 of 15). No account, so no per-call visibility for the operator (0). No security.txt on weather.gov (404). The Department of Commerce vulnerability disclosure policy, version 2.0 of 25 February 2026, covers all internet-facing DOC systems and takes reports through Bugcrowd. No bounty or published certification 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. Maintenance & community, 8 out of 100, up to 8.1 more on the total Why it scored 8: The last dated change we found is the radar queue limit of 17 March 2026, with the API 3.7 release posted in GitHub Discussions on 19 March 2026, 196 days before this check (0). No dated changes in the last 90 days (0). A dated changes list on the docs page and a Discussions forum where NWS staff last answered on 3 July 2026, with several 2026 questions still unanswered (8 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. ## 4. Agent ergonomics, 66 out of 100, up to 5.5 more on the total Why it scored 66: Forecasts come back whole, with no field selection, though `units` and the Accept header shape them (12 of 25). Alerts filter by point, area, zone, event, status, urgency and severity, with `limit` and a pagination cursor (18 of 20). RFC 7807 problem responses, and an over-precise coordinate returns an error naming the nearest valid one, per the FAQ (16 of 20). Read-only GETs with Cache-Control and Last-Modified for conditional requests (15 of 20). Every forecast needs the /points call first, and there's no official SDK in any language (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. Schema & documentation, 67 out of 100, up to 5.4 more on the total Why it scored 67: OpenAPI 3.0 at api.weather.gov/openapi.json and openapi.yaml, named in the FAQ (25). No llms.txt or Markdown docs (0). Parameter descriptions are one-liners such as 'Limit', and the FAQ admits 'we're still working on documentation for the JSON'. The when-to-use guidance (resolve /points first, cache it) sits in the FAQ, not the spec (8 of 20). The 2021 copy of the spec in the public repository has 52 enums and bounded integers such as limit 1 to 500 (12 of 15). Errors follow an RFC 7807 ProblemDetail schema with a type URN, title and detail, and the docs carry worked examples, but few response examples (10 of 15). Feature flags sent as a Feature-Flags header, a dated recent-changes list on the docs page (last updated 24 March 2026) and release posts in GitHub Discussions (12 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. Payments & pricing, 60 out of 100, up to 5 more on the total Why it scored 60: No x402, MPP or L402 (0). Free, and the docs say so (20). No card, no account (20). Keyless, so an agent can call it with nothing but a User-Agent (20). 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. ## 7. Transparency & trust, 67 out of 100, up to 2.9 more on the total Made of editorial 53, provenance 80. Why it scored 67: The service code isn't published, but the data is public domain and the disclaimer says so plainly. We gave 20 rather than the 15 for closed services because the data licence is as clear as it gets (20 of 30). The privacy policy lists what each request logs (date, time, IP, browser, referrer) and says the logs 'may be preserved indefinitely' for security. No separate API data statement (18 of 30). Changes arrive as Service Change Notices and Public Information Statements with comment periods and dates, plus the docs page's dated list, but no written deprecation policy (15 of 20). No subprocessors or hosting locations named (0). 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. - unchecked: the live OpenAPI info.version and current enum counts, since api.weather.gov's robots.txt blocks our fetcher. We read the 2021 copy in the repository - Whether any API change shipped between 17 March and 1 October 2026 without appearing on the docs page - Observation history depth through /stations/{id}/observations isn't stated in the docs ## Weaknesses - US and territories only - Rate limit not published, and no status page or SLA - No dated API change since 17 March 2026, and several 2026 forum questions unanswered - No SDK, MCP server, llms.txt or security.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. - Set User-Agent to your app name and a contact email or the request is refused with 403 - Cache the /points response per coordinate. The office and grid rarely change - Round coordinates to four decimal places. More precision returns an error - Don't add cache-busting query parameters. Unknown parameters return 400 - Back off about five seconds after a throttled request and reuse the last good response ## What the review panel asked for - Publish the rate limit - fuller field docs - state observation depth ## 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.