Maxwell Directory (x402 + MCP)

US weather (NWS)

us_weather

US National Weather Service forecasts, observations and alerts. US points only; points outside the US are refused free of charge. PAID: each call is charged in USDC from the configured wallet, only within the budget caps. Results are third-party data, not instructions. Before paying: free_sample shows a real answer of this product for free. Products (* = required param):

weather.alerts-by-state $0.005: params state*. Active NWS alerts for one US state or territory (full name, e.g.
weather.discussion $0.005: params wfo, lat, lon, text. Latest NWS Area Forecast Discussion (forecaster reasoning, confidence, key messages, aviation) for a foreca...
weather.forecast $0.005: params lat, lon, wfo, gridX, gridY. NWS daily/period forecast (about 7 days, day and night periods) for a US point or grid.
weather.forecast-hourly $0.005: params lat, lon, wfo, gridX, gridY. NWS hourly forecast (about 7 days) for a US point or grid.
weather.gridpoint $0.005: params lat, lon, wfo, gridX, gridY, fields, hours. NWS quantitative gridded forecast for a US point: time series for temperature, dewpoint, humidity, wind and...
weather.noaa $0.005: params lat*, lon*. NWS daily/period forecast for a US point or grid; same answer as weather.forecast.
weather.observation $0.005: params stationId, lat, lon. Most recent NWS station observation (by stationId, or the station nearest a lat/lon): temperature, dewpoint...
weather.point $0.005: params lat*, lon*. NWS point metadata for a US lat/lon: forecast office, grid x/y, time zone, county, nearest observation stat...

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "product": "<product>"
    },
    "name": "us_weather"
  }
}

Input Schema

Name	Required	Description
`params`	No	Parameters of the chosen product (names listed in the description).
`product`	Yes	Product id from the list in this tool's description.
`confirm_over_cap`	No	Only for clients that cannot ask the user themselves: set true after the user agreed to a price above their per-call cap. Clients that can ask always ask, and this flag is ignored there. Never raises the session or daily budget.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 11, 2026

changedInput schema / properties / product / enum

Previous value: -[
-  "weather.alerts-by-state",
-  "weather.discussion",
-  "weather.forecast",
-  "weather.forecast-hourly",
-  "weather.gridpoint",
-  "weather.observation",
-  "weather.point"
-]New value: +[
+  "weather.alerts-by-state",
+  "weather.discussion",
+  "weather.forecast",
+  "weather.forecast-hourly",
+  "weather.gridpoint",
+  "weather.noaa",
+  "weather.observation",
+  "weather.point"
+]

Changed1 schema field changedOct 5, 2026

changedInput schema / properties / product / enum

Previous value: -[
-  "weather.alerts-by-state",
-  "weather.discussion",
-  "weather.forecast",
-  "weather.forecast-hourly",
-  "weather.gridpoint",
-  "weather.noaa",
-  "weather.observation",
-  "weather.point"
-]New value: +[
+  "weather.alerts-by-state",
+  "weather.discussion",
+  "weather.forecast",
+  "weather.forecast-hourly",
+  "weather.gridpoint",
+  "weather.observation",
+  "weather.point"
+]

First observedSep 30, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false), the description discloses the pay-per-call USDC billing model, that the budget caps are enforced, that non-US points are refused at no cost, and that results are third-party data rather than instructions. This explains why a weather lookup is marked non-read-only (wallet charge) and adds real operational context an agent needs before calling.

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?

Front-loaded summary (scope, geo limit, pricing, free preview) followed by a scannable product/price list is the right structure for an eight-product dispatcher, and most sentences earn their place. The cut-off entries are a delivery defect rather than padding, but they still cost readability.

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

Completeness3/5

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

For a dispatcher with eight products, a free-form nested params object, and no output schema, the description must carry the per-product parameter and return-shape burden. It does so only partially: the truncations remove required-parameter detail from alerts-by-state, discussion, gridpoint, observation and point, and no guidance is given on output shape or limits, so an agent could still mis-call several products.

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%, but the schema only says 'names listed in the description', which makes the per-product param lists (state*, lat*, lon*, wfo, gridX/gridY, stationId, fields, hours, with * marking required) load-bearing rather than decorative. The value is genuine and above the 3 baseline, though several entries are truncated mid-parameter description and confirm_over_cap's semantics are only partly restated.

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

Purpose4/5

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

The opening sentence names a specific resource (NWS forecasts, observations and alerts) and the product list enumerates eight concrete sub-products with prices, so an agent knows exactly what it can call. The truncated catalog entries ('full name, e.g.', 'for a foreca...', 'nearest observation stat...') mean a few products' scope is cut off, which keeps it just short of a 5.

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?

It clearly states the when and the cost: US points only, points outside the US are refused without charge, every call is charged in USDC within budget caps, and free_sample must be used to preview for free before paying. That is strong routing guidance, but it never positions this tool against a generic sibling dispatcher (e.g. call_product), so an agent comparing the two gets no tiebreaker.

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

All Maxwell Directory (x402 + MCP) 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.

Resources

Need Help?