# Fix list: Weatherbit API From Anchor Terminal's listing at https://www.anchorterminal.com/tools/weatherbit, the October 2026 research run, assessed 8 October 2026. Grade C, 57.7 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 Weatherbit 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. Security & auth, 39 out of 100, up to 10.7 more on the total Why it scored 39: One plain key per account on Free, Standard and Plus, up to 10 on Business. It is accepted only as the `key` query parameter, so it lands in URLs and logs, and the spec lists http beside https (20 less 10, 10 of 30). Read-only data with nothing to approve (15 of 20). Alert titles and descriptions are relayed from meteorological agencies, and the rest is numeric (10 of 15). Quota counters come back in response headers and from /subscription/usage, but no per-call log for the account holder was found in the docs (4 of 15). security.txt returns 404, and no disclosure policy, bounty or certification was found on the site (0). 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. ## 2. Payments & pricing, 30 out of 100, up to 8.8 more on the total Why it scored 30: No x402, MPP or L402 in the docs, the spec or the pricing page (0). Plan prices are public without a login, with daily quotas and no per-call or overage price. The page showed us pounds only, £40, £179 and £410 a month (10 of 20). A free plan at 50 requests a day and a 21-day Business trial, neither needing a card (20). A person signs up in a browser to get a 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. ## 3. Maintenance & community, 21 out of 100, up to 6.9 more on the total Why it scored 21: The latest dated API announcement on the blog is 1 August 2025, 433 days before this check. The help article on the rate limit headers was updated on 9 July 2026, 91 days before, and the docs' sample responses are dated June 2026, so we scored the last visible change as within 180 days (10 of 30). No dated changelog entry falls in the last 90 days (0 of 20). A public blog for API updates that has gone quiet, a help centre with articles edited in 2026, and email support with a stated three business day response that we did not test (6 of 15). pyweatherbit 2.2.2 on PyPI dates from 14 February 2024 and is the only official SDK (3 of 15). Its repository has no CI and no commit since 13 February 2024 (2 of 10). 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, 61 out of 100, up to 6.3 more on the total Why it scored 61: This is an API with no MCP server. `days` and `hours` cap forecast length and `include` adds minutely data, alerts or lightning only on request. There is no field selection, and a daily forecast row carries about 40 fields (14 of 25). Date ranges, `units`, `lang` and a one-month cap per historical call. No pagination is needed (13 of 20). Five status codes with a JSON `error` string and no machine-readable code. 204 with an empty body means no data, and 403 covers both a missing key and a plan without access (12 of 20). All 21 endpoints are read-only GETs, safe to retry (15 of 20). Only `key` and a location are required and units default to metric. One official SDK, pyweatherbit for Python, last released in February 2024 (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. ## 5. Schema & documentation, 72 out of 100, up to 4.6 more on the total Why it scored 72: Swagger 2.0 at weatherbit.io/static/swagger.json, version 2.0.0, with 21 GET paths, 37 response models and bodies for 400, 403, 429 and 500. It declares no security definition and lists plain http as a scheme (23 of 25). No llms.txt, which returns 404, and no Markdown docs found (0). Each endpoint page lists parameters, return fields with types and a quota estimate, and warns against station lookups, but says little on when to pick one endpoint over another (13 of 20). `units` and `lang` are enums, 31 enum parameters in all. Location is six optional parameters with none marked required, and `include` and `days` carry no constraints in the spec (11 of 15). Request examples in curl, Ruby, Node.js and Python, sample responses and a status table with example bodies. Errors are one free-text string (12 of 15). The path is versioned as /v2.0. The changelog is a blog whose latest API post is dated 1 August 2025 (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. ## 6. Transparency & trust, 63 out of 100, up to 3.2 more on the total Made of editorial 42, provenance 84. Why it scored 63: Closed service with terms updated on 1 May 2025 that set out a commercial licence for paid plans and a Creative Commons non-commercial licence for the free plan. The terms say BY-NC-SA 4.0 and the pricing page links BY-NC 4.0. The Python SDK is MIT (15 of 30). The privacy policy, updated 26 December 2023, covers the API, lists what is logged (IP address, user agent, requested locations) and keeps request logs for no more than two weeks and account records for up to ten years. No DPA was found (17 of 30). No deprecation policy was found, and the terms let Weatherbit end access at any time without notice or reason, though they promise seven days' notice before a renewal when a paid subscription is ended without cause (2 of 20). Stripe and Google Analytics are named. Hosting is given as the United States and Canada, while the help centre says North America and Europe and our call was answered from a region labelled EU (8 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): - Domain age: weatherbit.io, registered 2016-12-25 (9 years) (11 of 15) - Terms of service: read, states 5 of the 7 things a reader expects (8.3 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. Reliability, 91 out of 100, up to 1.8 more on the total Why it scored 91: Graded as a hosted service. Status page at status.weatherbit.io on UptimeRobot, with API Central, East and West as monitors and 90 days of daily figures (20). All three show 100 per cent over 90 days, and the event feed lists nothing between 8 September and 8 October 2026 (30). Requests per day and per second are published for every plan, 50 and 1 on Free up to 2 million and 150 on Business (15). 429 is documented for both limits, every response carries X-RateLimit-Limit, X-RateLimit-Remaining and X-RateLimit-Reset, and the help centre says to slow down or retry. No Retry-After or backoff schedule was found. Every call is a GET (11 of 15). The pricing table lists 99.5 per cent uptime on paid plans, which the help centre calls best effort, with custom SLAs on request and no published credits (5 of 10). The v2.0 API is 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. ## 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 plan prices in US dollars. The pricing page served pounds to us and fills the numbers by script, and billing currency is chosen after login, so unitPrices is empty - unchecked: GitHub stars for weatherbit/weatherbit-python, because the GitHub API refused our request - Whether the account dashboard shows a per-call log or lets a key be rotated. The docs we read do not say - Whether the API accepts the key in a header. Only the query parameter is documented - The privacy policy says hosting is in the United States and Canada, while the help centre says North America and Europe and the API answered us with api_region: EU - The lead said the free tier includes a 16-day daily and a 240-hour hourly forecast and history. The plan table gives Free a 7-day daily forecast only, hourly from Standard and history from Plus - Email support response times are the vendor's statement and were not tested ## Weaknesses - The key is accepted only as the `key` query parameter, and the spec lists plain http as a scheme - Free plan is 50 requests a day, non-commercial, with a 7-day daily forecast and no hourly forecast or history - The last dated API announcement on the blog is 1 August 2025, and the Python SDK was last released in February 2024 - No security.txt, disclosure policy, certification or DPA found on the site - The terms let Weatherbit end access at any time without notice or reason, and no deprecation policy was 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. - Pass lat and lon. City, postal code and station lookups are accepted, but the docs recommend coordinates and mark station ID as use with caution - Read X-RateLimit-Remaining and X-RateLimit-Reset on each response. Daily quotas reset at 00:00 UTC and a spent quota returns 429 until then - Treat HTTP 204 with an empty body as no data found, not as an error - Split historical requests into ranges of one month or less. History needs the Plus plan or higher and has its own daily quota - Keep the key out of logs. It is part of the URL on every call, so always use https://api.weatherbit.io/v2.0 ## 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.