# Fix list: Google Weather API (Maps Platform) From Anchor Terminal's listing at https://www.anchorterminal.com/tools/google-weather-api, the October 2026 research run, assessed 1 October 2026. Grade B, 67 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 Google Weather API (Maps Platform): 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, 25 out of 100, up to 9.4 more on the total Why it scored 25: No x402, MPP or L402 (0). Tiered per-1,000 prices published without login, $0.15 per 1,000 to 100,000 down to $0.038 above 5 million (20). 10,000 free events a month, but only on a project with billing attached. The Maps Demo Key needs no billing and is for prototyping only (5 of 20). A person sets up a Cloud project and billing account 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. ## 2. Maintenance & community, 20 out of 100, up to 7 more on the total Why it scored 20: The last Weather API release note is the alerts endpoint going GA on 18 November 2025, 317 days ago. The discovery document's revision 20260930 is a routine regeneration, not a dated change (0). No dated releases in the last 90 days (0). Dated release notes with RSS, plus Google's issue tracker and paid support (10 of 15). Google's Maps Grounding Lite MCP server, which includes weather lookup, is in the registry as com.googleapis.mapstools/mcp, version 1.0.0 of 19 April 2026. It's a separate product, so partial credit (10 of 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. ## 3. Security & auth, 71 out of 100, up to 5.1 more on the total Why it scored 71: Google Cloud API keys can be restricted to the Weather API and to IPs or apps, and rotated. OAuth 2.0 is available but only with the broad cloud-platform scope. The documented examples put the key in the `key` query parameter, so we deducted 10 (20 of 30). Read-only data (15 of 20). Alerts text comes from national agencies (10 of 15). Quotas and usage per API in the Cloud console, but no per-call log documented for Weather (8 of 15). ISO/IEC 27001 and 27017, SOC 2 and SOC 3 listed on the Maps Platform trust centre, and a valid security.txt on google.com per the 30 September check (18 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. ## 4. Agent ergonomics, 79 out of 100, up to 3.4 more on the total Why it scored 79: `days` and `hours` size each forecast, and Google's Maps Grounding Lite MCP server has three tools, one of them weather lookup. No weather-specific field selection documented (22 of 25). `pageSize` and `pageToken` on every lookup (20). Google's standard error body with code, message and status, but no Weather-specific error table (15 of 20). Read-only GETs (15 of 20). Only a location is required and metric is the default. We didn't find a Weather client library (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. Reliability, 85 out of 100, up to 3 more on the total Why it scored 85: The Google Maps Platform status dashboard lists Weather API as its own product (20). It shows no Weather API incidents in the last 90 days. The one Maps incident in the period, 26 July 2026, hit traffic data and other APIs, not Weather (30). Default quota of 6,000 queries a minute, published in the FAQ and adjustable in the Cloud console (15). No 429, Retry-After or backoff guidance found in the Weather docs (0). Weather API is listed as a Maps Platform Core Service under the SLA, 99.9 per cent monthly uptime with credits of 10 to 50 per cent (10). Current conditions, forecasts, history and alerts are GA, and the minute forecast is Experimental (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, 82 out of 100, up to 2.9 more on the total Why it scored 82: A Google discovery document at weather.googleapis.com (revision 20260930) defines seven methods, 47 or more enums and a description on every parameter (25). No llms.txt or Markdown twin found (0). Method docs state what each returns, and the coverage page says where alerts apply (16 of 20). Typed parameters with enums for units, conditions and event types, `days` and `hours` bounds and a required location (14 of 15). Request and response examples, and the FAQ documents the 404 for unsupported locations. Errors otherwise follow Google's generic error model (12 of 15). Versioned v1 path, dated release notes with launch stages and an RSS feed (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, 75 out of 100, up to 2.2 more on the total Made of editorial 65, provenance 85. Why it scored 75: Closed service with Maps Platform terms last modified 26 August 2026 (15). Google's privacy policy, the Controller-Controller Data Protection Terms and GDPR, LGPD and Standard Contractual Clauses commitments on the trust centre agree with each other (22 of 30). The terms promise 12 months' notice before discontinuing a GA service or making a backwards-incompatible API change (20). The trust centre covers compliance frameworks, but we didn't find a Weather or Maps subprocessor list or data locations (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): - Endpoint on the vendor's domain: weather.googleapis.com is not on google.com (0 of 15) ## 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. - Whether US and Canadian alerts are covered. The coverage table as we read it didn't show them - Whether failed calls count as billable events - No Weather-specific 429 or retry guidance found ## Weaknesses - History is 24 hours only, and bulk data isn't available - Storing data outside the service and training or testing models on it are barred - A Cloud project with billing is needed before production use - No release note since 18 November 2025, and no llms.txt - Minute forecast is Experimental and outside the deprecation promise ## 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. - Ask for only the days or hours you need, one location a call. Every call is one billable event - Page with pageSize and pageToken rather than asking for 240 hours at once - Check the coverage page before promising alerts. Coverage is by country - Refetch rather than cache. The Maps terms give no caching window for weather content - Restrict the key to the Weather API and your server IPs in the Cloud console ## What the review panel asked for - Free tier without billing - state US alert coverage - a longer history window ## 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.