# Fix list: AccuWeather Core Weather API + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/accuweather-api, the October 2026 research run, assessed 1 October 2026. Grade D, 48.8 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 AccuWeather Core Weather API + MCP: 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: A plain key, sent as a Bearer header on REST. The MCP authentication page documents an `apikey` URL parameter as the alternative, so we deducted 10. Keys can be rotated on the subscriptions page, with no scopes or IP limits found (12 of 30). Read-only API and a read-only MCP server (17 of 20). Alerts and indices text comes from AccuWeather and national agencies (10 of 15). No per-call log found (0). No security.txt on developer.accuweather.com or www.accuweather.com (both 404), and no disclosure policy, bounty or certification found (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, 25 out of 100, up to 9.4 more on the total Why it scored 25: No x402, MPP or L402 (0). Package prices and per-1,000 overage rates are public, from $2 a month for 15,000 calls with $0.25 per 1,000 over (15 of 20). A 14-day trial at 500 Core Weather calls a day. Neither the FAQ nor llms-full.txt says whether it needs a card, so we gave half (10 of 20). A person signs up 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. ## 3. Maintenance & community, 13 out of 100, up to 7.6 more on the total Why it scored 13: No release notes or changelog. The only dated change we found is the API terms update of 28 April 2026, 156 days ago (10). No dated changes in the last 90 days (0). Support through a contact form, with no public changelog or community channel (3 of 15). The official MCP server isn't in the registry, which lists only a community server, and there's 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. Reliability, 65 out of 100, up to 7 more on the total Why it scored 65: Status page at status.accuweather.com with Enterprise API and Developer Portal API components (20). The front page showed 'No incidents reported' for each day from 16 to 30 July 2026, the history page didn't render for us and the incidents feed is closed to crawlers, so we read only part of the record (15 of 30). Call quotas published per package, 500 a day on the trial up to 2.4 million a month on Elite, but no per-second limit (15). 429 and 503 are defined in the status code table, with no Retry-After or backoff guidance. The best-practices page says to refresh on the Expires header (5 of 15). No SLA, and the terms cap liability at $100 (0). 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. ## 5. Schema & documentation, 60 out of 100, up to 6.5 more on the total Why it scored 60: No OpenAPI or other machine-readable contract found. The MCP tools page lists each tool's arguments, which we couldn't check as JSON Schema without a key (8 of 25). llms.txt, llms-full.txt and a .md twin for every docs page (10). The MCP tools page says what each tool returns and where coverage stops, such as MinuteCast and Lightning staying on REST (14 of 20). Parameters are documented, mostly location keys, language codes and booleans (10 of 15). Quick-start examples and an 11-row status code table, with RFC 7807 problem bodies carrying type, title, status and trace (13 of 15). Versioned /v1 paths, but no changelog or release notes anywhere on the portal (5 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. Agent ergonomics, 60 out of 100, up to 6.5 more on the total Why it scored 60: 26 MCP tools with no toolsets or subset option found. REST responses shrink a little with `details=false` and by choosing the 1, 5, 10 or 15-day endpoint (15 of 25). No field selection or paging (10 of 20). RFC 7807 errors with a trace id and a documented status table (16 of 20). Read-only GETs, and the docs describe the MCP server as read-only (15 of 20). Every weather call needs a location key from a separate search call first, and there's no official SDK (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. ## 7. Transparency & trust, 60 out of 100, up to 3.5 more on the total Made of editorial 39, provenance 80. Why it scored 60: Closed service with API terms dated 28 April 2026 (15). The privacy policy, updated 31 October 2025, ties retention to the life of the account, and the API terms let AccuWeather keep and use request data such as locations and IPs. No DPA found (12 of 30). The terms say AccuWeather 'may change the APIs at any time without notice' (0). A provider list is linked and the privacy policy says data is processed in the United States (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): - 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: whether the 14-day trial needs a card - unchecked: status page history beyond 16 to 30 July 2026, since the history page didn't render and the incidents feed blocks crawlers - Whether the MCP tool schemas are typed JSON Schema and carry readOnlyHint, which needs a key to list - How AccuWeather reads the AI clause for agents that pass forecast data to a language model at answer time - Release dates of the MCP server and the Starter package, which the portal doesn't give ## Weaknesses - Terms forbid using the data to train, validate or otherwise inform any AI system - MCP access only on the trial and Elite ($500 a month) - No changelog, and the terms allow API changes without notice - Two calls per new place, a location key lookup then the forecast - No security.txt, SLA or official SDK ## 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. - Cache location keys. They don't change, and the lookup is the call worth saving - Use the geoposition search first when you hold coordinates, then the forecast tools with the key it returns - Send the key as a Bearer header, not in the MCP URL, so it stays out of logs - Send Accept-Encoding: gzip and refresh on the Expires header rather than a fixed timer - Show the AccuWeather name and logo next to the data, and keep nothing older than two weeks ## What the review panel asked for - State trial card needs - Add programmatic signup - clarify the AI clause - name the models ## 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.