Visual Crossing Weather API by Visual Crossing

# Fix list: Visual Crossing Weather API

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/visual-crossing, the October 2026 research run, assessed 1 October 2026. Grade C, 60.3 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 Visual Crossing Weather 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. Security & auth, 40 out of 100, up to 10.5 more on the total

Why it scored 40: The REST API takes the key only as the `key` query parameter, so we deducted 10. The MCP server takes it in an X-VC-API-Key header or through user or machine-to-machine OAuth once provisioned, and multiple API keys per account arrived in Q2 2026, which allows rotation (15 of 30). Read-only data (15 of 20). Alerts come from national weather agencies (10 of 15). We found no per-call log or usage view in the docs we read (0). No security.txt 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, 40 out of 100, up to 7.5 more on the total

Why it scored 40: No x402, MPP or L402 (0). $0.0001 a record on the Metered plan, published without login, though Professional and Corporate show no price (20). 1,000 records a day free with no card, per the pricing page (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. Reliability, 66 out of 100, up to 6.8 more on the total

Why it scored 66: Status page at status.visualcrossing.com, run on UptimeRobot, with 24-hour to 90-day uptime sections (20). Its monitor data didn't load for our fetcher and it showed no updates in the last seven days, so we couldn't read an incident record (5). Limits published with numbers, 1,000 records a day free, records per query and per bulk job, and concurrency of 1 on Free and Professional and 10 on Corporate (15). 429 is documented for exceeded limits and for too many concurrent jobs, with no Retry-After or backoff guidance found. Every call is a GET (8 of 15). The plan table lists 99.5 per cent uptime on Free and 99.9 on paid plans, but the terms only owe compensation where a plan includes crediting provisions (8 of 10). The Timeline API is generally available, with `flatjson` output marked beta (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.

## 4. Schema & documentation, 74 out of 100, up to 4.2 more on the total

Why it scored 74: OpenAPI 3.0.1, version 4.6, published as JSON, YAML and Swagger. It's thin, with no enums, terse parameter descriptions and only 200 responses defined (15 of 25). llms.txt at www.visualcrossing.com/llms.txt with sections for product facts, MCP and access (10). The Timeline docs explain each parameter and when to use date ranges, `include` and `elements` (14 of 20). `unitGroup`, `include` and `contentType` values are listed in the docs, not in the spec, and `elements` is a free list (9 of 15). Example requests for forecast, date range and single time, and a table of 400, 401, 404, 429 and 500 with causes (13 of 15). A public changelog grouped by quarter, most recently 4 September 2026, which says changes keep backwards compatibility unless noted (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.

## 5. Maintenance & community, 58 out of 100, up to 3.7 more on the total

Why it scored 58: The MCP guide was published on 24 September 2026 and the latest changelog entry is dated 4 September 2026 (30). Four additions in the Q3 2026 changelog, forecast model retrieval, forecast confidence and spread, wildfire events and twilight fields (20). A public changelog, and support by email and forum that we didn't test (8 of 15). The official MCP server isn't in the registry, where only a third-party Pipeworx wrapper appears, 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.

## 6. Agent ergonomics, 78 out of 100, up to 3.6 more on the total

Why it scored 78: `include` picks days, hours, current, alerts or stats and `elements` trims columns, so a call can be cut to a few fields. The MCP server has one tool (24 of 25). Date ranges, `include`, `elements`, `options=nonulls` and per-query record caps control output (18 of 20). Error codes come with causes and the body carries a message, but no machine-readable error key (15 of 20). Read-only GETs. The MCP guide doesn't mention tool annotations (14 of 20). Only a location is required, but `unitGroup` defaults to US units and the GitHub repository holds sample code, not an SDK (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.

## 7. Transparency & trust, 61 out of 100, up to 3.4 more on the total

Made of editorial 31, provenance 90.

Why it scored 61: Closed service with terms last updated January 2023 that set storage by licence level, bar resale and add a non-compete (15). The privacy policy, updated 23 May 2025, states no retention periods, says nothing about what API requests log and doesn't mention a DPA (8 of 30). The changelog promises backwards compatibility unless noted, but there's no deprecation policy or dated notice (8 of 20). No subprocessors or data locations named, beyond Google tags on the site (0).

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)

## 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: incident history on status.visualcrossing.com, whose monitor data didn't load for our fetcher
- Whether paid plans' 99.9 per cent uptime comes with service credits
- Whether the account dashboard shows per-call usage

## Weaknesses

- Key only in the query string on the REST API
- OpenAPI spec defines no enums and no error responses
- Privacy policy states no retention periods or subprocessors
- Storing results needs the right licence level, and the terms carry a non-compete
- No security.txt, disclosure policy or MCP registry entry

## 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.

- Always pass include= and elements=. A bare call returns days, hours and current for every element and burns records
- Count records before a backfill. Hourly data is 24 records a day, so a year for one place is 8,760
- Pass unitGroup=metric. The default is US units
- Use the MCP server with X-VC-API-Key rather than pasting the key into a URL
- Keep to one request at a time on Free and Professional. A second concurrent job returns 429

## What the review panel asked for

- Add agent API signup
- publish forecast cadence

## 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.