FiatDock

Weather forecast for any point (MET Norway, 9 days) ($0.0018)

weather_forecast

Read-onlyIdempotent

PAID ($0.0018 USDC via x402). Forecast for any coordinate from MET Norway's Locationforecast 2.0 (global): the current hour (temperature, humidity, wind, cloud, next-hour rain, symbol), rows up to hours ahead (1 h steps ~2.5 days, then 6 h, each stating its period), and up to 9 UTC-day rows with min/max (incl. MET's 6-hour extremes), total precipitation and the main condition. Times UTC; MET's CC BY 4.0 attribution included. No air quality or alerts. Upstream failure is not charged. Without payment this returns the 402 challenge; the fiatdock-mcp npm package pays automatically. Any answer the tool cannot produce is >= 400 and is NOT charged.

Input Schema

Name	Required	Description
`lat`	No	Latitude in decimal degrees, -90 to 90 (required with lon; an empty body answers the published example point)
`lon`	No	Longitude in decimal degrees, -180 to 180 (required with lat)
`days`	No	How many daily summary rows (UTC calendar days, today first), 1-9 (default 3)
`hours`	No	How many hours ahead the `hourly` rows reach, 1-72 (default 24). Steps are 1 h for about the first 2.5 days and 6 h after
`payment`	No	Base64 of a single x402 v2 PaymentPayload (EIP-3009 transferWithAuthorization on Base USDC). OMIT it on the first call: the 402 you get back carries `howToPay.payloadTemplate` — the exact envelope to fill in — plus the price and the EIP-712 domain. Send it on the second call to complete the purchase; it is forwarded as the PAYMENT-SIGNATURE header, never as body data. Nothing is charged for the 402 itself, and a call that fails after payment settles nothing.

Output Schema

Name	Required	Description
`asOf`	Yes	ISO time the forecast was read from MET (or revalidated as unchanged)
`note`	Yes	How to read the rows (UTC times, step lengths, daily rules) and their limits
`daily`	Yes	One row per UTC day, today first: min/max temperature, total precipitation, main condition
`units`	Yes	The unit of every number
`hourly`	Yes	Forecast rows from now for `hours` hours: 1-hour steps for about 2.5 days, then 6-hour steps
`source`	Yes	Where the data came from
`current`	Yes	The forecast for the hour now falls in (a forecast, not an observation)
`location`	Yes	The point forecast (rounded to 4 decimals) and its elevation above sea level as MET models it
`defaulted`	No	Present only when the body was empty: which point the answer is for, and why
`attribution`	Yes	The credit MET Norway's licence (CC BY 4.0 / NLOD 2.0) requires — keep it beside any use of the data
`forecastEndsAt`	Yes	The last forecast time MET publishes for this point (about 9-10 days ahead)
`modelUpdatedAt`	Yes	When MET last updated this forecast (meta.updated_at)

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 9, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only cover read-only/idempotent/openWorld, yet the description discloses far more: exact price and payment rail (x402 USDC), the 402 challenge behavior, that upstream failures and >=400 answers are NOT charged, that payment is forwarded as a header never body data, and the CC BY 4.0 attribution. This is unusually rich behavioral context beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense but front-loaded with the PAID marker, and each sentence carries real information. Minor redundancy around the payment/charging rules, but it is appropriately sized for a paid, multi-call-flow tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given an output schema exists, return values need not be explained, yet the description still maps the output rows precisely and covers the full payment lifecycle including failure non-charging. Nothing an agent needs to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, and the description adds value by clarifying the hourly step structure (1 h then 6 h) and that daily rows are UTC-day summaries with min/max. It reinforces rather than merely restates the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Forecast for any coordinate from MET Norway's Locationforecast 2.0'), names the provider and global scope, and enumerates the shape of the returned data (current hour, hourly rows, daily rows). No weather sibling exists to confuse it with, and an agent can immediately tell what it gets.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete usage context: it is paid, it excludes air quality and alerts, and it explains the two-call payment flow (omit `payment` first, send it on the second). It does not point to an alternative tool for the uncovered data (alerts/AQ), but the when-to-use and how-to-call guidance is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All FiatDock tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.