# Fix list: OpenWeather One Call API From Anchor Terminal's listing at https://www.anchorterminal.com/tools/openweather-one-call, the October 2026 research run, assessed 1 October 2026. Grade C, 57.4 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 OpenWeather One Call 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, 45 out of 100, up to 11 more on the total Why it scored 45: No public status page found, and status.openweathermap.org doesn't resolve (0). No incident history to read (5). Limits published with numbers, 1,000 One Call calls a day free, a default cap of 2,000 a day you can change, and 60 a minute on the Free plan (15). 429 is documented as quota exceeded, and the agent lane says its 429 names the interval to wait. All calls are GETs (10 of 15). The subscription table publishes uptime of 95 to 99.9 per cent for the Startup to Expert plans, but nothing for One Call by Call (5 of 10). One Call 4.0 is the current version (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, 42 out of 100, up to 10.1 more on the total Why it scored 42: The REST API takes the key only as the `appid` query parameter, so it lands in URLs and logs (20 less 10). The agent lane sends a data key as a Bearer header and keeps a separate account secret for balance and top-ups, though data keys have no scopes (12 of 30). Read-only data. The MCP server adds account tools, and a top-up needs a person on the payment page (15 of 20). Alerts text comes from national weather agencies (10 of 15). The agent lane has a balance route with bought and free credits per product, but we found no per-call log (5 of 15). No security.txt (404 per the 30 September check), no disclosure policy, bounty or certification found (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. Schema & documentation, 68 out of 100, up to 5.2 more on the total Why it scored 68: No OpenAPI for the main REST API. The agent lane links an openapi.yaml and an errors.json dictionary, which we couldn't parse, so partial credit (12 of 25). llms.txt on openweathermap.org and on the agent lane, with a Markdown guide and llms-full.txt (10). Each response field is described, and the 3.0 page tells new integrations to use 4.0 (14 of 20). `exclude` and `units` values are listed in the docs, not in a contract (10 of 15). JSON examples for every endpoint, and errors documented as 400, 401, 404, 429 and 5xx with a `cod`, `message` and `parameters` body (15). Versioned paths, but no public changelog and no date for retiring 3.0 (7 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. ## 4. Payments & pricing, 60 out of 100, up to 5 more on the total Why it scored 60: No x402, MPP or L402. The agent lane's top-ups are card only and need a person (0). Per-call prices published without login, $0.0015 a call on One Call by Call and $0.001 a call on the agent lane (20). The agent lane gives every account 1,000 One Call credits a day with only an email (20). POST an email to agents.openweathermap.org/v1/accounts and the data key comes back in the response (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. ## 5. Agent ergonomics, 73 out of 100, up to 4.4 more on the total Why it scored 73: `exclude` drops current, minutely, hourly, daily or alerts blocks on 3.0, and 4.0 splits the timeline by step (1 minute, 15 minutes, hour, day). The MCP server has six tools (20 of 25). 4.0 takes a `start` parameter to page through timelines (16 of 20). Error bodies carry a code and message, and the agent lane's errors.json gives each code with its HTTP status and the reaction to take (18 of 20). Read-only GETs, and the agent lane bills only 2xx responses. We didn't see MCP annotations (14 of 20). Three required parameters, but `units` defaults to Kelvin and there's no official SDK (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. ## 6. Maintenance & community, 60 out of 100, up to 3.5 more on the total Why it scored 60: The MCP server's version 0.3.0 was published to the registry on 4 September 2026 and the agent terms were revised to version 2026-09-23-1 (30). Two MCP versions on one day and a terms revision in the last 90 days, but no dated API changelog (10 of 20). No public changelog for One Call. Support is through the help desk, which we didn't test (5 of 15). The MCP server is in the official registry as org.openweathermap/agents, a domain-verified namespace (15). 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. ## 7. Transparency & trust, 62 out of 100, up to 3.3 more on the total Made of editorial 53, provenance 70. Why it scored 62: Closed service. The terms of sale put the data under CC BY-SA 4.0 and ODbL per the 30 September check, which is clearer than most (18 of 30). The privacy policy, last updated 18 July 2022, says API request parameters, IPs and user agents aren't collected or stored and keeps customer records six years. The agent lane runs under a second company, Extreme Electronics Ltd, with its own terms, and we found no DPA (18 of 30). 3.0 is marked deprecated with no date (5 of 20). Google Analytics and group companies in Latvia and the USA are named for transfers (12 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) - Changelog: 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 agent lane's openapi.yaml came back as binary to our fetcher, so we didn't read its operations - Whether the agent lane's /v1/account/verify route must be called before the data key works - Whether One Call by Call can start without a card on file. The FAQ mentions a billing form and month-end charging but doesn't say - The listing's agent note about X-Cost-Charged and X-Cost-Remaining headers is contradicted by the agent llms.txt, which says no response carries a cost or balance - The release date of One Call 4.0 isn't on the docs page ## Weaknesses - The main API takes the key only as the appid query parameter - 3.0 is marked deprecated with no shutdown date, and 4.0 needs new paths - No status page, public changelog or OpenAPI for the main API - No security.txt or disclosure policy found - Agent top-ups are card only and need a person, and the lane is run by Extreme Electronics Ltd ## 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. - Sign up on the agent lane with POST https://agents.openweathermap.org/v1/accounts and keep the data key. It's shown once - Check GET https://data.openweathermap.org/account/balance for credit. No data response carries a cost or balance - On the main API, activate One Call by Call and set the daily cap in Billing plans before the first loop - Pass units=metric. The default is Kelvin - Use exclude=minutely,alerts on 3.0, or the 4.0 timeline step you need, to shrink responses ## What the review panel asked for - Document the verify step - Accept x402 top-ups - a methodology page - a 3.0 shutdown date ## 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.