Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add smarterweather/developer --skill smarterweather-mcpgit clone --depth 1 https://github.com/smarterweather/developerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/smarterweather/developer/smarterweather-mcp)<a href="https://agentmods.dev/skills/smarterweather/developer/smarterweather-mcp"><img src="https://agentmods.dev/badge/skills/smarterweather/developer/smarterweather-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/smarterweather/developer/smarterweather-mcp"><img src="https://agentmods.dev/badge/skills/smarterweather/developer/smarterweather-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00143 | $0.01598 |
| Opus 5.5 | $0.00057 | $0.00639 |
| Sonnet 5.5 | $0.00029 | $0.00320 |
| Haiku 4.5 | $0.00014 | $0.00160 |
Grade A, and why
smarterweather-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use the Smarter Weather MCP servers
Smarter Weather ships two hosted MCP servers on different hosts; they
do not conflict, but they serve different phases. The onboarding MCP
is one-shot: keep it in the client config only until configure_mcp
has written the weather MCP entry, then remove it so its account tools
are not left in a long-lived session.
Coverage: Smarter Weather covers the 50 US states and DC only. The
US territories (Puerto Rico, the US Virgin Islands, Guam, the Northern
Mariana Islands and American Samoa) and other countries are outside it.
Weather tools return an outside-coverage error for a point outside the
50 states and DC. Tell the user, and do not retry the same place as
lat,lon.
| Server | Endpoint | Auth | Purpose |
|---|---|---|---|
| Weather MCP | https://mcp.smarterweather.com |
API key Bearer or keyless x402 | Hosted weather tools. The root URL serves the core and catalog toolsets: forecasts, current conditions, alerts, observed rain, probabilities, catalog search and raw dataset queries. Every other tool is reachable from the same connection: find_tools lists outlooks and forecaster text (guidance), rendered radar/satellite/sounding imagery (visual) and the other toolsets, and call_tool runs one, with no reconnect. Claude Code connected over HTTP (claude mcp add --transport http) gets every toolset at the root URL; through the stdio bridge it gets core and catalog plus find_tools and call_tool. /x/all, or /x/<toolset>[,<toolset>] (also X-SW-Toolsets), lists the toolsets directly. |
| Onboarding MCP | https://mcp.developers.smarterweather.com |
Anonymous for discovery; OAuth for account tools | One-time onboarding: get_plans, get_documentation, sign_up, then create_api_key, configure_mcp, usage + billing |
Tool descriptors for the weather MCP: https://developers.smarterweather.com/.well-known/mcp-tools.json
Recommended onboarding flow (agents)
- Prefer the CLI with no MCP host when you can:
- Human present:
npx -y @smarterweather/mcp-onboarding@latest login - No human:
npx -y @smarterweather/mcp-onboarding@latest trial
- Human present:
- Or connect to the onboarding MCP with no credentials, call
get_plans/get_documentation/sign_up, complete Clerk OAuth (stdio bridge loopback on port3334), thencreate_api_key/configure_mcp. Via the stdio bridge, create/rotate sink into.env. - Point
@smarterweather/mcp-weatherat the project.env(envFileor cwd fallback). Remove the onboarding server afterwards.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed 81fb4e59e10a
- yesterday Changed 485c8a342525
- 10d ago Changed · +11 lines 021f8b1385d0
- 1mo ago Changed · +2 lines 554de9f80753
- 1mo ago Changed · +3 lines 9408141b2acd
- 1mo ago First seen · 112 lines · 143 tokens per session scan A b41891f429ce
smarterweather-mcp is a skill published in the GitHub repository smarterweather/developer (1 stars, last pushed today), licensed MIT. It adds 143 tokens to every session and 1,598 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
headless-step-provision-wordpress
Provision a headless WordPress backend for the Hostinger Headless flow: create the headless website with WordPress at /cms, verify and self-heal, then record it in site.json.
Contract-First Testing
Contract-first testing approach using Pact, Spring Cloud Contract, or Dredd for ensuring API consumer-provider compatibility.
headless-step-check-state
First build step of the Hostinger Headless flow, run right after connect. Works out where a given domain's build stands — is a run already in progress, does the site already exist, how far did it get — by reconciling the global workspace state under /.hostinger/ / with what the Hostinger connector reports, then guides…
headless-step-content-model
Step 4 (content model) of the Hostinger Headless flow. Prepare phase: turns brief.md into a content helper (content-model.md) — fixed Title/Description plus a tailored generation prompt per section (Navigation, Pages, Articles) — and generates the drafts/images, no live backend needed. Push phase: routes to the…
headless-step-frontend
Step 6 (frontend) of the Hostinger Headless flow. Builds the website that renders the backend's content. Figures out (or confirms) the framework — defaulting to Next.js SSR — implements the look already chosen in design.md (the design step's contract), and builds the source into src/. Only ask for the clarifications…
troubleshoot-website
Diagnose and fix a website on Hostinger web hosting (Shared, Cloud or Agency plans) that is down, slow, erroring, insecure or failing to build. Checks the site from outside, reads builds, runtime logs, WordPress health, SSL, cache and PHP settings through the Hostinger MCP, names the cause with evidence, and applies…