WeatherAPI.com by WeatherAPI.com (Zoomash Ltd)

# Fix list: WeatherAPI.com

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/weatherapi-com, the October 2026 research run, assessed 1 October 2026. Grade B, 65.8 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 WeatherAPI.com: 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, 37 out of 100, up to 11 more on the total

Why it scored 37: The key goes only in the `key` query parameter, so it lands in URLs and logs (20 less 10). Business adds IP blocking (12 of 30). Read-only data (15 of 20). Alerts come from government agencies (10 of 15). We found no per-call log in the docs (0). No security.txt (an HTML error page per the 30 September check), 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, 30 out of 100, up to 8.8 more on the total

Why it scored 30: No x402, MPP or L402 (0). Plan prices are public, from $7 a month for 3 million calls, but there's no per-call or overage price (10 of 20). Free at 100,000 calls a month with no card (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, 45 out of 100, up to 4.8 more on the total

Why it scored 45: Five changelog entries dated July 2026, such as ECMWF IFS and AIFS blended into the forecast and wet-bulb temperature, 63 to 92 days before this check (20). Those five entries fall in the last 90 days if dated after 3 July, which month-level dates don't show, so we gave 15 of 20. A public changelog, and support by email we didn't test (8 of 15). The official MCP server isn't in the registry, where a third-party Pipeworx wrapper is, and the SDKs haven't changed since 2020 and 2021 (0). The npm package weatherapi-mcp is at 1.0.0, and its repository has had no commit since the initial release on 22 March 2026, with no CI (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, 80 out of 100, up to 3.3 more on the total

Why it scored 80: `current_fields`, `day_fields` and `hour_fields` trim responses, and `aqi`, `alerts` and `days` keep them small. The official MCP server has 11 tools (22 of 25). `days`, `hour`, field filters and bulk requests on Pro+ (17 of 20). Numeric error codes such as 1006 (no location found) and 2007 (quota exceeded) let an agent tell the cases apart (18 of 20). Read-only GETs, and the bulk POST only reads. The MCP tools carry no readOnlyHint annotations (13 of 20). Only `key` and `q` are required, and SDKs exist for Node.js, Java, PHP and Go, but none has a commit since 2021 (10 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. Transparency & trust, 70 out of 100, up to 2.6 more on the total

Made of editorial 49, provenance 90.

Why it scored 70: Closed service with terms under English law. The MCP server is MIT (15). The privacy policy is undated, names no entity beyond WeatherAPI.com, logs IP and location, gives no retention periods and leaves template placeholders in its deletion section (8 of 30). The terms promise 12 months' written notice before an API deprecation and 90 days before changes to access rights (18 of 20). Stripe is named, and transfers to the USA, Russia, Japan, China and India are disclosed, but no hosting provider (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):

- security.txt: not found (0 of 10)

## 6. Reliability, 90 out of 100, up to 2 more on the total

Why it scored 90: Status page at status.weatherapi.com on Better Stack, with api.weatherapi.com and the website as components (20). It lists no incidents, and api.weatherapi.com shows 100 per cent over 30 days. The website component shows 99.243 per cent, which isn't the API (30). Monthly call quotas published for every plan, 100,000 free up to 10 million on Business (15). A spent quota returns 403 with error code 2007, distinct from auth errors, but there's no 429, Retry-After or backoff guidance (5 of 15). The terms promise 99.9 per cent to High Volume customers with service credits, and the plan table lists uptime per plan (10). 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.

## 7. Schema & documentation, 89 out of 100, up to 1.8 more on the total

Why it scored 89: OpenAPI 3.1.0 at weatherapi.com/openapi.json, version 1.0.2, 12 paths with a structured ErrorResponse on 400, 401 and 403 (25). llms.txt at weatherapi.com/llms.txt, published April 2026 per the changelog (10). Endpoint descriptions state purpose and note plan limits (16 of 20). Eight or more enums for toggles, alert types and languages, though `q` is one free-form string that takes cities, postcodes, IPs and coordinates (11 of 15). Eleven numbered error codes with HTTP status and message, plus an API explorer (14 of 15). A changelog dated by month, most recently July 2026, and a versioned /v1 path (13 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.

## 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 July 2026 changelog entries fall before or after 3 July, since they're dated by month
- The changelog names ECMWF IFS and AIFS and METAR, but there's no methodology page, so dataQuality.sourcesDisclosed stays false
- Whether the account dashboard shows per-call usage
- The listing said only a community MCP server existed. The vendor publishes weatherapi-mcp on npm, which we've added to notable

## Weaknesses

- Key only in the query string, and no security.txt
- Privacy policy undated, with template placeholders and transfers to Russia and China
- SDKs for Node.js, Java, PHP and Go untouched since 2020 and 2021
- No full list of data sources or models
- Caching limited to 60 minutes for current and 24 hours for forecast

## 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 current_fields, day_fields or hour_fields to cut the response to what you need
- Treat a 403 with error code 2007 as the monthly quota, not a bad key. There's no 429
- Reuse the id from search.json (q=id:NNN) to avoid ambiguous city names
- Cache history freely, current for under an hour and forecasts for under a day, to stay inside the terms
- Use https://api.weatherapi.com/v1. The docs still show an http:// base URL

## What the review panel asked for

- State trial card needs
- a methodology page

## 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.