\n\n[](https://github.com/cyanheads/aviation-weather-mcp-server/releases/latest/download/aviation-weather-mcp-server.mcpb) [](https://cursor.com/en/install-mcp?name=aviation-weather-mcp-server&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBjeWFuaGVhZHMvYXZpYXRpb24td2VhdGhlci1tY3Atc2VydmVyIl19) [](https://vscode.dev/redirect?url=vscode:mcp/install?%7B%22name%22%3A%22aviation-weather-mcp-server%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40cyanheads%2Faviation-weather-mcp-server%22%5D%7D)\n\n[](https://www.npmjs.com/package/@cyanheads/mcp-ts-core)\n\n
\n\n---\n\n## Tools\n\nFive tools covering aviation weather — station lookup, current observations, terminal forecasts, pilot reports, and active advisories:\n\n| Tool | Description |\n|:-----|:------------|\n| `aviation_find_stations` | Resolve airports and weather stations by ICAO ID, bounding box, or US state. Returns ICAO/IATA/FAA IDs, coordinates, elevation, and available data types. |\n| `aviation_get_metar` | Get current weather observations (METARs) for one or more airports. Returns decoded wind, visibility, ceiling, present weather, temp/dewpoint, altimeter, cloud layers, flight category (VFR/MVFR/IFR/LIFR), and the raw METAR string. |\n| `aviation_get_taf` | Get Terminal Aerodrome Forecasts for one or more airports. Returns each forecast period with valid times, surface wind, low-level wind shear, visibility, decoded weather, cloud layers, and vertical visibility into a forecast obscuration, plus the raw TAF string. |\n| `aviation_get_pireps` | Get recent Pilot Reports near an airport or within a bounding box. Returns decoded turbulence, icing, and cloud reports with altitude, aircraft type, intensity, and the raw PIREP string. |\n| `aviation_get_advisories` | Get active domestic SIGMETs for a region. Returns hazard type (CONVECTIVE, TURBULENCE, ICING, IFR), severity, altitude range, valid period, polygon coordinates, and raw text. |\n\n### `aviation_find_stations`\n\nResolve and discover weather stations by multiple search modes.\n\n- Look up one or more stations by 4-letter ICAO ID (up to 20 IDs per call) — lookup is ICAO-only, but each returned record includes its IATA/FAA aliases when available\n- Discover all stations within a geographic bounding box\n- List stations for one of the 50 US states or DC via two-letter USPS code (uses bbox + client-side state filter)\n- Returns `data_types` (METAR, TAF, etc.) so agents can confirm what's available before querying\n- Every result states whether the upstream 400-row cap cut it, so a truncated draw is never mistaken for every station in the area — a capped state query also reports the row count from before the state filter, and a smaller `bbox` is the named lever\n\n---\n\n### `aviation_get_metar`\n\nFetch current or recent METAR observations (1–10 stations per call).\n\n- `hours` parameter (1–12) returns observation history per station; default 1 returns only the most recent\n- Flight category (VFR/MVFR/IFR/LIFR) is returned directly from the AWC API — no client-side computation needed\n- Decodes cloud layers, wind with gusts, visibility, and present weather (the raw groups plus plain English, one reading per group) in addition to the raw METAR string\n- Ceiling covers broken, overcast, and obscuration layers, and reports whether the height was measured or is an indefinite ceiling — vertical visibility into an obscuration\n- METAR type field distinguishes `METAR` (routine) from `SPECI` (special observation triggered by significant weather change)\n- Every batch reports which of the requested stations came back, so a partial result is never mistaken for full coverage — missing IDs are named with recovery guidance\n\n---\n\n### `aviation_get_taf`\n\nFetch Terminal Aerodrome Forecasts for 1–4 airports.\n\n- Returns structured forecast periods with change types (`FM`, `TEMPO`, `BECMG`) and probabilities\n- Forecast weather decoded group by group beside the raw groups (`-SHRA BR` → `light rain showers; mist`), the same shape `aviation_get_metar` returns\n- Forecast obscurations keep their layer and carry the vertical visibility into them (`VV002` → a 200 ft indefinite ceiling), rather than reading as a clear sky\n- Low-level wind shear (`WS020/20040KT`) is decoded to the shear-layer top and the forecast wind at that height\n- `valid_from` / `valid_to` in ISO 8601 for straightforward time comparisons\n- Every batch reports which of the requested stations came back, so a partial result is never mistaken for full coverage — missing IDs are named with recovery guidance\n\n---\n\n### `aviation_get_pireps`\n\nSearch for recent Pilot Reports by station+radius or bounding box.\n\n- `station_id` + `distance_nm` (10–500 nm, 100 when omitted) for radial search around an airport\n- `bbox` for geographic area search — useful for en-route corridor checks; `distance_nm` has no meaning here and is rejected alongside it\n- `altitude_min_ft` / `altitude_max_ft` filters to isolate reports at cruise altitude, either bound alone or both (min must not exceed max)\n- Turbulence and icing arrays include up to two layers per report (as reported by the API)\n- Every result states whether the upstream 400-row cap cut it, naming `bbox`, `distance_nm`, and `hours` as the levers that narrow a query before the cap applies — the altitude filter runs after it and cannot recover a dropped report\n- Note: absence of PIREPs does not mean smooth conditions — they are sparse by nature\n\n---\n\n### `aviation_get_advisories`\n\nList currently active domestic SIGMETs.\n\n- `advisory_type` filter: `sigmet` or `all` (default) — both return the active SIGMET set\n- `hazard` filter: `CONVECTIVE`, `TURBULENCE`, `ICING`, `IFR`\n- `bbox` filter applied client-side (AWC API returns all active advisories; the tool filters by polygon overlap)\n- AIRMETs are not served. The upstream feed carries domestic SIGMETs only, so `advisory_type: airmet` and the `MTN OBSCN`, `SURFACE WIND`, and `LLWS` hazards are rejected with guidance rather than answered with SIGMETs or an empty array\n- During fair-weather periods, no SIGMETs may be active — an empty result is a valid state, not an error\n\n---\n\n## Prompts\n\n| Type | Name | Description |\n|:-----|:-----|:------------|\n| Prompt | `aviation_preflight_brief` | Structure a preflight weather briefing for one or more airports. Guides the LLM to call `aviation_get_metar`, `aviation_get_taf`, and `aviation_get_advisories` in sequence and synthesize a go/no-go picture with flight categories and active hazards. |\n\nAll resource data is reachable via tools. This server has no resources — all aviation weather data is time-sensitive (METARs valid ~1 hour, advisories minutes to hours) and unsuitable for stable-URI resources.\n\n---\n\n## Features\n\nBuilt on [`@cyanheads/mcp-ts-core`](https://www.npmjs.com/package/@cyanheads/mcp-ts-core):\n\n- Declarative tool and prompt definitions — single file per primitive, framework handles registration and validation\n- Unified error handling — handlers throw, framework catches, classifies, and formats\n- Pluggable auth: `none`, `jwt`, `oauth`\n- Structured logging with optional OpenTelemetry tracing\n- STDIO and Streamable HTTP transports\n\nAviation-weather-specific:\n\n- Keyless — no API key or authentication required; all data is from the public AWC Data API\n- Single service (`aviation-weather-service`) with retry + exponential backoff for the keyless public endpoint\n- Raw coded strings (`rawOb`, `rawTAF`, `rawAirSigmet`) surfaced alongside decoded fields so agents have both layers\n- State→bbox table enables US-state station queries that the AWC API doesn't natively support\n- Server-level `instructions` field surfaces the \"not an official briefing\" safety disclaimer to all clients on `initialize`\n\nAgent-friendly output:\n\n- Flight category (`VFR`/`MVFR`/`IFR`/`LIFR`) as a discriminated string field — agents can branch on it without parsing ceiling + visibility\n- Structured error contracts with typed `reason` fields and `recovery` hints (e.g., \"Verify ICAO IDs with `aviation_find_stations`\")\n- `aviation_preflight_brief` prompt encodes the correct METAR → TAF → PIREPs → advisories briefing sequence that agents frequently get wrong by omitting steps\n\n---\n\n## Getting started\n\n### Public Hosted Instance\n\nA public hosted instance is available at `https://aviation-weather.caseyjhand.com/mcp`. Add it to your MCP client configuration:\n\n```json\n{\n \"mcpServers\": {\n \"aviation-weather\": {\n \"type\": \"streamable-http\",\n \"url\": \"https://aviation-weather.caseyjhand.com/mcp\"\n }\n }\n}\n```\n\n### Self-hosted / local\n\nAdd the following to your MCP client configuration file.\n\n```json\n{\n \"mcpServers\": {\n \"aviation-weather\": {\n \"type\": \"stdio\",\n \"command\": \"bunx\",\n \"args\": [\"@cyanheads/aviation-weather-mcp-server@latest\"],\n \"env\": {\n \"MCP_TRANSPORT_TYPE\": \"stdio\",\n \"MCP_LOG_LEVEL\": \"info\"\n }\n }\n }\n}\n```\n\nOr with npx (no Bun required):\n\n```json\n{\n \"mcpServers\": {\n \"aviation-weather\": {\n \"type\": \"stdio\",\n \"command\": \"npx\",\n \"args\": [\"-y\", \"@cyanheads/aviation-weather-mcp-server@latest\"],\n \"env\": {\n \"MCP_TRANSPORT_TYPE\": \"stdio\",\n \"MCP_LOG_LEVEL\": \"info\"\n }\n }\n }\n}\n```\n\nOr with Docker:\n\n```json\n{\n \"mcpServers\": {\n \"aviation-weather\": {\n \"type\": \"stdio\",\n \"command\": \"docker\",\n \"args\": [\n \"run\", \"-i\", \"--rm\",\n \"-e\", \"MCP_TRANSPORT_TYPE=stdio\",\n \"ghcr.io/cyanheads/aviation-weather-mcp-server:latest\"\n ]\n }\n }\n}\n```\n\nFor Streamable HTTP, set the transport and start the server:\n\n```sh\nMCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http\n# Server listens at http://localhost:3010/mcp\n```\n\n### Prerequisites\n\n- [Bun v1.3.0](https://bun.sh/) or higher (or Node.js v24+).\n- No API key required — the AWC Data API is fully public and keyless.\n\n### Installation\n\n1. **Clone the repository:**\n\n```sh\ngit clone https://github.com/cyanheads/aviation-weather-mcp-server.git\n```\n\n2. **Navigate into the directory:**\n\n```sh\ncd aviation-weather-mcp-server\n```\n\n3. **Install dependencies:**\n\n```sh\nbun install\n```\n\n4. **Configure environment:**\n\n```sh\ncp .env.example .env\n# edit .env if you need to override AWC_BASE_URL or AWC_TIMEOUT_MS\n```\n\n---\n\n## Configuration\n\n| Variable | Description | Default |\n|:---------|:------------|:--------|\n| `AWC_BASE_URL` | Base URL for the NWS AWC Data API. | `https://aviationweather.gov/api/data` |\n| `AWC_TIMEOUT_MS` | Per-request timeout in milliseconds (1000–60000). | `10000` |\n| `MCP_TRANSPORT_TYPE` | Transport: `stdio` or `http`. | `stdio` |\n| `MCP_HTTP_PORT` | Port for HTTP server. | `3010` |\n| `MCP_SESSION_MODE` | HTTP session handling: `auto` (resolves to `stateful`), `stateful`, or `stateless`. The shipped `.env.example` and Docker image pin `stateless` — no tool here needs a multi-round-trip input. | `stateless` |\n| `MCP_AUTH_MODE` | Auth mode: `none`, `jwt`, or `oauth`. | `none` |\n| `MCP_LOG_LEVEL` | Log level (RFC 5424). | `info` |\n| `OTEL_ENABLED` | Enable [OpenTelemetry instrumentation](https://github.com/cyanheads/mcp-ts-core/tree/main/docs/telemetry). | `false` |\n\nSee [`.env.example`](./.env.example) for the full list of optional overrides.\n\n---\n\n## Running the server\n\n### Local development\n\n- **Build and run:**\n\n ```sh\n bun run rebuild\n bun run start:stdio\n # or\n bun run start:http\n ```\n\n- **Run checks and tests:**\n\n ```sh\n bun run devcheck # Lint, format, typecheck, security\n bun run test # Vitest test suite\n bun run lint:mcp # Validate MCP definitions against spec\n ```\n\n### Docker\n\n```sh\ndocker build -t aviation-weather-mcp-server .\ndocker run --rm -p 3010:3010 aviation-weather-mcp-server\n```\n\nThe Dockerfile defaults to HTTP transport, stateless session mode, and logs to `/var/log/aviation-weather-mcp-server`. OpenTelemetry peer dependencies are installed by default — build with `--build-arg OTEL_ENABLED=false` to omit them.\n\n---\n\n## Project structure\n\n| Directory | Purpose |\n|:----------|:--------|\n| `src/index.ts` | `createApp()` entry point — registers tools/prompts and inits services. |\n| `src/config` | Server-specific env var parsing (`AWC_BASE_URL`, `AWC_TIMEOUT_MS`). |\n| `src/services/aviation-weather` | AWC Data API client — HTTP fetch, retry with exponential backoff, response normalization. |\n| `src/mcp-server/tools` | Tool definitions (`*.tool.ts`). |\n| `src/mcp-server/prompts` | Prompt definitions (`*.prompt.ts`). |\n| `tests/` | Unit and integration tests mirroring `src/`. |\n\n---\n\n## Development guide\n\nSee [`CLAUDE.md`](./CLAUDE.md) for development guidelines and architectural rules. The short version:\n\n- Handlers throw, framework catches — no `try/catch` in tool logic\n- Use `ctx.log` for request-scoped logging, `ctx.state` for tenant-scoped storage\n- Register new tools and prompts via the barrels in `src/mcp-server/*/definitions/index.ts`\n- Wrap external API calls: validate raw → normalize to domain type → return output schema; never fabricate missing fields\n\n> **Not an official preflight briefing.** Data from the AWC is informational only. Real flight planning requires an authorized source (e.g., Leidos/1800wxbrief.com). The server surfaces this disclaimer via its `instructions` field sent on every `initialize`.\n\n---\n\n## Contributing\n\nIssues and pull requests are welcome. Run checks and tests before submitting:\n\n```sh\nbun run devcheck\nbun run test\n```\n\n---\n\n## License\n\nApache-2.0 — see [LICENSE](LICENSE) for details.\n",
"bytes": 15264,
"sha": "043d45d831dd455195950eb96354e01d73cdedfd9a5b12de505fb1c8fd03c594",
"repo_slug": "cyanheads/aviation-weather-mcp-server",
"fonte": "repo",
"truncated": false,
"api": "https://agentalog.com/api/listings/mcp_io_github_cyanheads_aviation_weather_mcp_2a8f72d2/readme"
}