WildFireBot MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Set by the host. When present the server serves HTTP on 0.0.0.0:$PORT at /mcp. | |
| FIRMS_MAP_KEY | Yes | NASA FIRMS MAP key. Required for fire detections. Sign up at https://firms.modaps.eosdis.nasa.gov/api/area/ | |
| AIRNOW_API_KEY | No | Optional AirNow API key for nearest monitors. Request at https://docs.airnowapi.org/account/request/ | |
| OPENAQ_API_KEY | No | Optional OpenAQ API key for open measurements. See https://docs.openaq.org/using-the-api/quick-start | |
| WFB_RATE_LIMIT | No | Requests per client IP per window. Default 60 per 60 s; 0 disables rate limiting. | |
| WFB_ACCESS_TOKEN | No | Optional. If set, clients must send Authorization: Bearer <token>. If unset the server is open. | |
| WFB_RATE_WINDOW_S | No | Rate limit window in seconds. Default 60. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
WildFireBot estimates relative smoke exposure from satellite fire detections and forecast wind. The score is not an official AQI and not a health advisory. This is an estimate of relative smoke exposure from satellite fire detections and forecast wind. It is not a health advisory, not a regulatory AQI, and not a substitute for AirNow, local smoke outlooks, or medical guidance.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| forecast_smokeA | Estimate relative wildfire smoke exposure at one latitude and longitude from NASA FIRMS fire detections and an Open-Meteo wind forecast. Returns nearby fire clusters, a wind summary, an hourly smoke-exposure score, nearby PM2.5 readings when monitors respond, degraded-mode notices, and a disclaimer. The score is a relative exposure index, not an official AQI and not a health advisory. Reads FIRMS_MAP_KEY, AIRNOW_API_KEY, and OPENAQ_API_KEY from the environment. A missing key is named in notices; the server keeps running. |
| forecast_smoke_aqiA | Forecast PM2.5 and the US EPA AQI at one latitude and longitude. Adds a Gaussian plume from each NASA FIRMS fire cluster, using fire radiative power and the Open-Meteo wind forecast, on top of Open-Meteo's background PM2.5. Works for a new fire because it does not need a history of observations. Returns horizons, degraded-mode notices, and a disclaimer. This is a screening estimate, not an official AQI and not a health advisory. Missing FIRMS_MAP_KEY, AIRNOW_API_KEY, or OPENAQ_API_KEY is reported in notices. |
| pm25_to_aqiA | Convert one PM2.5 concentration in micrograms per cubic meter to the US EPA 2024 AQI with the breakpoint equation. Does not compute a 24-hour average or a NowCast. The result includes the AQI, the category, and a disclaimer that this is not a health advisory. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
The three tools target distinct outputs: relative smoke exposure, unit conversion, and PM2.5/AQI forecasting. The two forecast tools share similar names and inputs, but their descriptions clearly separate a relative exposure index from a concentration-and-AQI plume estimate. An agent could still briefly hesitate between forecast_smoke and forecast_smoke_aqi, so it is not perfectly crisp.
All names use consistent snake_case and readable domain terms. The patterns are not strictly identical: forecast_smoke and forecast_smoke_aqi are verb_noun forms, while pm25_to_aqi is a conversion-style name. This is a minor deviation, not a confusing mix of conventions.
Three tools is lean but well matched to a focused smoke-exposure and AQI screening server. Each tool covers a distinct operation, and there are no redundant or filler tools. The surface is intentionally narrow rather than under-scoped.
The core workflow is covered: estimate smoke exposure, forecast PM2.5/AQI, and convert PM2.5 to AQI. Minor gaps exist, such as no direct tool to inspect raw FIRMS clusters or retrieve standalone PM2.5 observations, but agents can still complete the main screening tasks. These gaps are workable rather than blocking.