Stormglass API

# Fix list: Stormglass API

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/stormglass, the October 2026 research run, assessed 9 October 2026. Grade E, 39.9 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 Stormglass 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, 34 out of 100, up to 13.2 more on the total

Why it scored 34: Graded as a hosted service. No status page was found. The site, the docs and the terms link none (0). With no page there is no incident history to read (5). Daily quotas are published for every plan, 10, 500, 5,000 and 25,000 requests, with no per-second figure (12 of 15). The docs give 402 for a spent quota and 503 with try again later, and every response carries `dailyQuota` and `requestCount`. The FAQ says a spent quota returns Too Many Requests, which disagrees with the docs, and no Retry-After or backoff guidance was found. Every call is a GET (7 of 15). No SLA was found and the terms say the service is not warranted to be uninterrupted (0). The v2 API 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. Schema & documentation, 40 out of 100, up to 9.8 more on the total

Why it scored 40: No OpenAPI file or other machine-readable contract was found in the docs (0 of 25). llms.txt returns 404. The docs site is Docsify, so each of its eleven pages is also a plain Markdown file, which is how we read them (5 of 10). Each endpoint page states its purpose, and the weather page points to the historical endpoint for past data and explains the `sg` source. The sources page gives resolution, update frequency and forecast span per model (12 of 20). Parameter tables mark required fields and defaults, and `datum` lists its seven values, but no types or ranges are given (7 of 15). Examples in Python, curl and JavaScript with sample responses, and a table of seven error codes. The sample JSON has trailing commas, and the descriptions of the three secondary swell fields are swapped (10 of 15). The path is versioned as /v2 and 410 marks legacy resources. No changelog was found, only blog posts about new sources (6 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.

## 3. Security & auth, 44 out of 100, up to 9.8 more on the total

Why it scored 44: One plain key per account, sent in the `Authorization` header and never in the URL. The docs describe no scopes, rotation or revocation (15 of 30). Read-only data with nothing to approve (15 of 20). Responses are numeric values with station names and source labels (10 of 15). `requestCount` and `dailyQuota` come back with each response, and no per-call log was found in the docs (4 of 15). security.txt returns 404, and no disclosure policy, bounty or certification was found. The terms say the security of transmitted information is not guaranteed (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.

## 4. Payments & pricing, 25 out of 100, up to 9.4 more on the total

Why it scored 25: No x402, MPP or L402. The API's 402 means a spent quota (0). Plan prices are public without a login, in euros, with daily quotas and no per-call or overage price, 19, 49 and 129 euros a month (10 of 20). A free plan at 10 requests a day. The site says signup is always free. The signup form is drawn by script and we did not read it, so whether a card is asked for is not established, and the terms call the plan an evaluation not meant for indefinite use (15 of 20). A person signs up in a browser to get a key (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.

## 5. Maintenance & community, 15 out of 100, up to 7.4 more on the total

Why it scored 15: The latest dated announcement is the ERA5 blog post of 26 February 2026, 225 days before this check. The docs files carry a Last-Modified header of 29 June 2026, 102 days before, and the terms are dated 17 March 2026, so we scored the last visible change as within 180 days (10 of 30). No dated entry falls in the last 90 days (0 of 20). The blog announced new sources in May and September 2025 and twice in February 2026. Support is by email and comes with the Medium plan and higher, which we did not test (5 of 15). No official SDK was found (0 of 15). There is no public package or repository to assess (0 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.

## 6. Agent ergonomics, 65 out of 100, up to 5.7 more on the total

Why it scored 65: This is an API with no MCP server. `params` chooses the fields returned, `source` the models, and `start` and `end` the hours. The default on `/weather/point` is every source, so each field comes back once per model unless `source` is set (20 of 25). Time ranges, a bounding box for tide stations and a 10-day cap per historical call. Nothing is paginated (14 of 20). Seven status codes are documented, and the 403 body we saw was `{"errors":{"key":"API key is invalid"}}`. 402 for a spent quota is unusual, the FAQ names a different code, and no body is documented for any error (11 of 20). All ten endpoints are read-only GETs, safe to retry (15 of 20). `lat`, `lng` and `params` are the only required inputs and times default to today in UTC. No official SDK was found (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.

## 7. Transparency & trust, 45 out of 100, up to 4.8 more on the total

Made of editorial 22, provenance 68.

Why it scored 45: Closed service with one short terms page, dated 17 March 2026. The FAQ limits commercial use to Medium and higher. The terms set no rules on storing, caching or redistributing data and do not say what licence the customer receives (10 of 30). The privacy text is a few paragraphs inside the terms. It says data is kept as long as necessary and account data until deletion, with no period for request data, and no DPA was found (8 of 30). No deprecation policy was found. The terms let the company modify or terminate any service at any time and change content without notice, and the docs list 410 for retired resources (1 of 20). HubSpot is the only third party named, and no hosting location is given (3 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: stormglass.io, registered 2018-01-30 (8 years) (11 of 15)
- Terms of service: read, states 4 of the 7 things a reader expects, and has 1 clause that costs points (5.4 of 10)
- Privacy policy: read, states 3 of the 8 things a reader expects (6.3 of 10)
- Status page: 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 signup form at dashboard.stormglass.io, which is drawn by script, so whether the free plan asks for a card is not established
- unchecked: whether the dashboard lets a key be rotated or shows a per-call log. The docs do not say
- The docs give 402 for a spent daily quota and the FAQ says Too Many Requests. Which one the API returns was not tested
- No status page was found. We did not guess at a status address
- The terms name Storm Glass AB under Swedish law but give no address or registration number
- The terms do not say whether API data may be stored or redistributed. This matters before any probe result is published
- weather.current is left out of capabilities. The API returns hourly series with no dedicated current-conditions endpoint, and the FAQ says it is not a live feed
- Prices are in euros only, so unitPrices is empty and nothing was converted
- The lead was right on vendor, URL, interface and docs link

## Weaknesses

- No OpenAPI file, llms.txt, official SDK or changelog was found. The docs are eleven Markdown pages
- No status page, SLA, security.txt, disclosure policy, certification or DPA was found, and the terms disclaim uninterrupted service
- Free plan is 10 requests a day, non-commercial, and the terms call it an evaluation plan not meant for indefinite use
- The docs give 402 for a spent daily quota and the FAQ says Too Many Requests. No Retry-After or per-second limit is documented
- The privacy text is a few paragraphs inside the terms, with no retention period or hosting location, and the terms allow changes to the service without notice

## 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.

- Send the key as `Authorization: KEY` with no Bearer prefix. A missing or wrong key returns 403 with `{"errors":{"key":"API key is invalid"}}`
- Always pass `source=sg` or a short source list on `/weather/point`. The default is every source, which multiplies the size of each hourly record
- Treat 402 as a spent daily quota, not a billing failure, and stop until the next day. Read `meta.requestCount` against `meta.dailyQuota` on each response
- Use `/historical/point` for past dates, at most 10 days a call and nothing newer than about 7 days. `/weather/point` looks back 14 days only
- Send and read all times in UTC. Tide sea levels are relative to the chosen datum (MSL by default) and are not water depth

## 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.