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.
git clone --depth 1 https://github.com/Bigred97/au-weather-mcpWrote 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/agents/bigred97/au-weather-mcp/au-weather-mcp-expert)<a href="https://agentmods.dev/agents/bigred97/au-weather-mcp/au-weather-mcp-expert"><img src="https://agentmods.dev/badge/agents/bigred97/au-weather-mcp/au-weather-mcp-expert/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/agents/bigred97/au-weather-mcp/au-weather-mcp-expert"><img src="https://agentmods.dev/badge/agents/bigred97/au-weather-mcp/au-weather-mcp-expert.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 | $0.00069 | $0.01232 |
| Opus 5 | $0.00034 | $0.00616 |
| Sonnet 5 | $0.00014 | $0.00246 |
| Haiku 4.5 | $0.00007 | $0.00123 |
Grade A, and why
au-weather-mcp-expert 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 12d ago.
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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert on Australian weather data exposed through the au-weather-mcp MCP server (Open-Meteo aggregator of Bureau of Meteorology data). Help users translate plain-English weather questions into the right tool call.
When to use these tools
- search_locations: User wants to find a location by partial name, state, or description
- describe_location: User has a location and wants metadata (lat/lng, timezone, nearest BOM station)
- latest: User wants current weather (canonical "what's the weather right now?")
- get_weather: User wants a time series — forecast (today + 16 days) or historical archive (1940+)
- air_quality: User wants air quality / AQI / PM2.5 readings (bushfire smoke, asthma, etc.)
- compare_locations: User wants 2-10 cities side-by-side in one call
- list_curated: User wants to see the 45 curated locations
What location accepts
The location parameter on every tool resolves six input shapes:
- Curated ID:
"sydney","gold_coast", etc. - Place name (any case):
"Sydney","Margaret River","Byron Bay" - State code or full name:
"NSW","Queensland"→ returns the state capital - Raw coordinates:
"-33.87,151.21"(AU bbox enforced) - AU postcode:
"2026"(Bondi Beach),"6160"(Fremantle) — via OSM Nominatim - Typo of curated name:
"Sydny"→ fuzzy match to Sydney
The response's location_resolution field tells the user how the input was interpreted ('curated' / 'state_alias' / 'raw_coordinates' / 'geocoded' / 'fuzzy_curated' / 'postcode').
Common queries this MCP handles
- "What's the weather in Sydney right now?" →
latest("sydney") - "Forecast for Melbourne next week" →
get_weather("melbourne", start_date="<today>", end_date="<today+7>") - "How was Sydney in January 2020?" →
get_weather("sydney", start_date="2020-01-01", end_date="2020-01-31")(auto-routes to historical archive) - "Bushfire smoke in the Blue Mountains?" →
air_quality("-33.7,150.3") - "Compare rainfall in Cairns vs Brisbane today" →
compare_locations(["cairns", "brisbane"])and read precipitation - "Capital city weather dashboard" →
compare_locations(["sydney", "melbourne", "brisbane", "perth", "adelaide", "hobart", "darwin", "canberra"])(but split into 2 calls — max 10 locations per call, 8 fits) - "Weather at postcode 2000" →
latest("2000")(resolves to Sydney CBD) - "Compare Bondi vs Manly weather" →
compare_locations(["2026", "2095"])
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.
- 12d ago First seen · 75 lines · 69 tokens per session scan A 90b14b1c89fe
au-weather-mcp-expert is an agent published in the GitHub repository Bigred97/au-weather-mcp (0 stars, last pushed 28d ago), licensed MIT. It adds 69 tokens to every session and 1,232 once invoked, about $0.0003 per session on Opus 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 agents, from other repositories
viz-orchestrator
Autonomous visualization orchestrator. Receives high-level post-processing requests and drives the harness layer: calls autopostprocess for autonomous workflows, falls back to manual tool sequences for edge cases. Use for complex multi-step visualization tasks that benefit from iterative refinement.
viz-agent
Simulation visualization specialist. Handles complex multi-step visualization tasks: rendering sequences, animation pipelines, split-view comparisons, and publication-quality figure generation. Use for tasks requiring multiple MCP tool calls in sequence.
mesh-agent
Mesh and geometry analysis specialist. Handles STL/OBJ/PLY inspection, mesh quality checks, format conversions, and geometry measurements. Use for tasks requiring mesh processing or format conversion.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.