Open-Meteo by Open-Meteo

# Fix list: Open-Meteo

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/open-meteo, the October 2026 research run, assessed 1 October 2026. Grade B, 63.5 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 Open-Meteo: 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, 38 out of 100, up to 10.9 more on the total

Why it scored 38: No credential for non-commercial use. Commercial keys go in the URL as `&apikey=`, a documented option (20 less 10, so 10). Read-only data (15 of 20). Numeric weather data with no third-party text (10). Paid plans get email alerts at 80, 90 and 100 per cent of the monthly budget, and the pricing page says a usage dashboard is still being built (3 of 15). No security.txt per the 26 September check, no SECURITY.md in the repository, and no bug bounty or certification found. Contact is info@open-meteo.com (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.

## 2. Reliability, 50 out of 100, up to 10 more on the total

Why it scored 50: StatusCake uptime page at status.open-meteo.com, which loads its monitors in the browser and has no incident write-ups we could find (15 of 20). We couldn't read any incident history (5). Free limits published as 600 calls a minute, 5,000 an hour, 10,000 a day and 300,000 a month (15). No 429 or Retry-After guidance found, and the terms allow blocking IPs without notice (0). Paid plans carry a 99.9% uptime target on reserved servers, a target rather than an SLA with remedies (5 of 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.

## 3. Payments & pricing, 50 out of 100, up to 6.3 more on the total

Why it scored 50: No x402, MPP or L402 (0). Plan volumes are on the pricing page (1M, 5M and 50M+ calls a month) but the prices appear only at Stripe checkout (10 of 20). Free for non-commercial use with no account or card (20). An agent can call it with no signup at all (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.

## 4. Schema & documentation, 77 out of 100, up to 3.7 more on the total

Why it scored 77: OpenAPI 3.1 files for nine APIs in the open-meteo repository, last updated 9 September 2026, with enums for every weather variable. Not linked from the docs pages (25). open-meteo.com/llms.txt returns 404, and the docs are an HTML page with a URL builder (0). Descriptions in the spec are one line per API, and the docs explain each variable and model but not when to pick one API over another (12 of 20). Typed parameters with enums and required latitude and longitude, though coordinates are strings so that lists fit (13 of 15). URL builder examples in the docs and a 400 response with `error` and `reason` in the spec (12 of 15). /v1 paths and a release-please CHANGELOG.md (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.

## 5. Agent ergonomics, 85 out of 100, up to 2.4 more on the total

Why it scored 85: You name the variables you want with `hourly=`, `daily=` or `current=`, and set `forecast_days`, `past_days` or a date range, so responses are as small as the question (22 of 25). Several coordinates and models in one call, no pagination needed (18 of 20). Errors come back as JSON with `error: true` and a readable `reason` (15 of 20). Read-only GETs with no side effects (15 of 20). Only latitude and longitude are required, and there are official SDKs for Python and TypeScript plus a FlatBuffers SDK repo (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. Transparency & trust, 73 out of 100, up to 2.4 more on the total

Made of editorial 70, provenance 76.

Why it scored 73: Server code under AGPL-3.0 and data under CC BY 4.0 (30). The terms say logs, including IP addresses, are deleted after 90 days, paid accounts keep only aggregated usage after that, and the site sets no cookies or trackers. No DPA found (25 of 30). The terms change 'effective immediately upon posting', and we found no deprecation policy or dated notices (5 of 20). Stripe and Substack are named, the entity is OpenMeteo GmbH in Switzerland, but hosting locations aren't stated (10 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: open-meteo.com, registered 2021-04-27 (5 years) (11 of 15)
- Changelog: not found (0 of 10)
- security.txt: not found (0 of 10)

## 7. Maintenance & community, 90 out of 100, up to 0.9 more on the total

Why it scored 90: Release 1.6.0 on 2026-09-10 (30). Five releases in the last 90 days, 1.5.4 and 1.5.5 on 11 July, 1.5.6, 1.5.7 and 1.6.0 in September (20). 123 commits since 3 July from five people plus Dependabot. We couldn't read issue response times in this run (15 of 25). Official SDK repositories for Python and TypeScript (15). CI test workflow and Dependabot on the main repository (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.

## 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.

- Commercial plan prices, which only appear at checkout
- What the API returns when a free client goes over its limits
- unchecked: GitHub issue response times

## Weaknesses

- Commercial prices appear only at Stripe checkout
- The commercial key is sent as `&apikey=` in the URL
- Status page is uptime monitors with no incident write-ups we could read
- Terms change on posting and IPs can be blocked without notice
- No llms.txt, no official MCP server, and the OpenAPI files aren't linked from the docs

## 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.

- Name only the variables you need in `hourly=` or `daily=`, because each one adds a full time series
- Credit 'Weather data by Open-Meteo.com' wherever you show the data
- Use customer-api.open-meteo.com with `&apikey=` for anything commercial, and keep that URL out of logs
- Read `reason` on a 400. It names the bad parameter
- Cache by coordinate and model run, since global models update about every six hours

## What the review panel asked for

- a deprecation notice period
- a date for cap enforcement
- llms.txt
- link the OpenAPI files

## 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.