# Tomorrow.io MCP > Tomorrow.io gives your AI agent real-time access to institutional-grade weather data. It handles hyperlocal forecasts, specialized environmental matrices like AQI and pollen counts, and complex hazard assessments for road risk or wildfire index. If your logic flow depends on knowing if it's safe to drive through a storm or what the air quality is today, this connector feeds that intelligence directly into your agent. ## Overview - **Category:** cloud-infrastructure - **Price:** Free - **Tags:** hyperlocal-forecast, climate-intelligence, environmental-data, real-time-monitoring, risk-assessment, meteorology ## Description Look, if your logic flow depends on knowing what the weather’s gonna do—and you know it does—this connector feeds all that intelligence right into your agent. You're getting institutional-grade data from Tomorrow.io, meaning you don't just get surface-level forecasts; you get hyper-specific environmental matrices for everything from pollen counts to road risk. **Getting Current Atmospheric Readings:** You can pull real-time conditions using **`get_realtime_weather`**. Just give it a location—a zip code, city, or lat/lon—and you'll get the current temperature, wind speed, pressure, and other atmospheric indicators right now. It’s what you use when your agent needs to know if it's raining *this second*. **Predicting Future Weather Patterns:** When predicting out, you've got options for every timescale. If you need a quick look at the big picture, **`get_daily_forecast`** gives you daily extremes and totals spanning up to 15 days. You can zoom in way deeper if you use **`get_hourly_forecast`**, which returns predictions hour-by-hour for up to 120 hours out. But sometimes, minutes matter—and they do. Use **`get_minutely_precipitation`** when you need minute-by-minute rain forecasts (nowcasts) for super precise planning. If the standard forecast tools don't cover the exact window your agent needs, use **`get_custom_timelines`**. This lets you query weather data over custom time ranges—you specify the arbitrary intervals, and it pulls the data. You’ll also want to check out specialized environmental forecasts: **`get_air_quality_index`** fetches current and forecasted air quality index (AQI) for any location. For allergy season planning, **`get_pollen_forecast`** gives you daily predictions specifically for pollen counts. And if there's a wildfire brewing, **`get_wildfire_risk`** pulls the current risk index alongside associated weather conditions. **Analyzing Road Travel Risk:** You can’t just look at the temperature and assume the roads are fine. You need to run specialized checks on road hazards using **`get_road_weather_risk`**. This tool generates specific assessments for driving safety, helping you plan routes around complex weather patterns like flash flooding or icy conditions. **Querying Environmental History:** Need to audit something? Want to train a model based on what actually happened last fall? Use **`get_historical_weather`**. You can retrieve actual recorded observations by specifying past dates and locations, letting your agent analyze outcomes from any time period in the past. This isn't theoretical data; it’s real-world records. Ultimately, this server gives your AI client everything it needs—from immediate atmospheric readings to 15-day projections, specialized hazard reports, and historical benchmarks. You'll feed all that depth directly into your agent's decision-making process. ## Tools ### get_air_quality_index Retrieves current and forecasted data on air quality indices for a specific location. ### get_custom_timelines Queries weather data for custom time ranges, allowing you to specify arbitrary intervals not covered by standard tools. ### get_daily_forecast Returns daily weather forecast extremes and totals spanning up to 15 days out. ### get_historical_weather Retrieves actual recorded weather observations for specified past dates and locations. ### get_hourly_forecast Returns hour-by-hour predictions for a given location, up to 120 hours into the future. ### get_minutely_precipitation Provides minute-by-minute precipitation forecasts (nowcasts) for high precision planning. ### get_pollen_forecast Retrieves daily predictions and indices specifically for pollen counts. ### get_realtime_weather Provides current, real-time weather conditions using a location identifier (lat/lon, zip, or city). ### get_road_weather_risk Generates assessments and predictions specifically for driving and road hazards based on weather. ### get_wildfire_risk Retrieves the current wildfire risk index alongside associated weather conditions. ## Prompt Examples **Prompt:** ``` What is the expected air quality index in New York over the next hour? ``` **Response:** ``` Based on the air quality data, the EPA Index for New York over the next hour is expected to be around '38', with the primary pollutant categorized as Fine Particulate Matter (PM2.5). The health concern reads as 'Good'. ``` **Prompt:** ``` Show me the minute-by-minute precipitation near Golden Gate bridge right now. ``` **Response:** ``` Over the next 60 minutes around the Golden Gate location, the predicted precipitation is registering strictly at 0.00 mm/hr continuously, indicating no expected rainfall directly matching those micro-coordinates. ``` ## Capabilities ### Get Current Atmospheric Readings Provides real-time weather data (temperature, wind speed, etc.) for a specific global location. ### Predict Future Weather Patterns Generates forecasts segmented by minute, hour, or full day over up to 15 days out. ### Assess Air Quality and Pollen Counts Retrieves current and forecast data for air quality index (AQI) and daily pollen density. ### Analyze Road Travel Risk Runs assessments specific to driving conditions, identifying potential road hazards due to weather. ### Query Environmental History Retrieves actual recorded weather observations by specifying past dates and fields for analysis. ## Use Cases ### Emergency Logistics Rerouting A logistics manager needs a route through three states. Instead of checking Google Maps, they ask their agent: 'Find me the safest route from A to C.' The agent runs `get_road_weather_risk` for every segment and automatically reroutes the fleet around areas flagged with high wind or ice risks. ### Annual Festival Planning An events coordinator needs to know if they need to reschedule an outdoor market. They ask their agent: 'What are the weather risks for October 15th?' The agent runs `get_daily_forecast` and cross-references it with expected high pollen counts from `get_pollen_forecast`, flagging potential conflicts weeks ahead. ### Industrial Site Monitoring An industrial safety team needs to know if their site is at risk. They ask: 'Is the area safe for outdoor work?' The agent uses `get_wildfire_risk` and `get_air_quality_index`. If either index spikes, the system automatically locks down access protocols. ### Insurance Claim Auditing An adjuster needs to validate a claim from last season. They ask: 'What were the precise conditions at this zip code on July 2nd?' The agent runs `get_historical_weather`, providing exact data points for rainfall, wind speed, and temperature. ## Benefits - You stop guessing about the weather. Using `get_road_weather_risk`, you get specific hazard assessments for vehicle routes, letting your agent automatically adjust delivery paths instead of just flagging 'rain.' - Forecasting is precise. Instead of a general daily forecast, tools like `get_minutely_precipitation` give you minute-by-minute rain predictions—critical when scheduling outdoor construction work. - Your health logic gets better data. By combining `get_air_quality_index` and `get_pollen_forecast`, your agent can issue alerts that account for both PM2.5 levels and seasonal allergies, which simple weather APIs miss. - Planning for the long term? The `get_daily_forecast` provides 15 days of total predictions, allowing you to schedule large-scale events or resource deployments weeks in advance. - You can audit anything that happened. If a project failed due to poor visibility last month, run `get_historical_weather` to pull the exact conditions for that date and location. ## How It Works The bottom line is: You just ask questions in plain language, and the server runs the complex weather models for you. 1. First, you must subscribe to the Tomorrow.io connector and provide your developer API Key in your agent's configuration. 2. Next, ask your AI client a query that requires weather data (e.g., 'What is the wildfire risk for Seattle next week?'). 3. The agent automatically invokes the correct tool—like `get_wildfire_risk` or `get_daily_forecast`—and uses the returned structured data to answer your prompt. ## Frequently Asked Questions **How do I check if there will be rain minute-by-minute using get_minutely_precipitation?** You must specify a location (lat/lon) and a time window. This tool gives you the highest level of temporal detail available, showing predicted precipitation in mm/hr at one-minute intervals. **Can I use get_historical_weather to prove weather for an insurance claim?** Yes. By defining the precise time boundaries and field sets you need (e.g., wind speed, precipitation), this tool pulls actual recorded data points, making it useful for audits and claims verification. **What is the difference between get_hourly_forecast and get_daily_forecast?** The hourly forecast breaks down predictions into 1-hour increments (up to 120 hours), giving you detailed timing. The daily forecast provides summarized extremes and totals over longer periods, up to 15 days. **Does get_road_weather_risk account for pollen counts?** No. `get_road_weather_risk` focuses strictly on driving hazards like ice, fog, and high winds. For allergens or air quality issues, you need to call the dedicated `get_pollen_forecast` or `get_air_quality_index` tools. **What happens if I try to use get_realtime_weather without an API key?** The request fails immediately with a 401 Unauthorized error. You must first subscribe to the service and configure your developer API Key within your agent's environment variables for any tool call to succeed. **Are there rate limits when I use get_hourly_forecast repeatedly?** Yes, all endpoints enforce rate limiting. If you exceed the allowed calls per minute, your agent will receive a 429 Too Many Requests status code. You'll need to build backoff logic into your workflow to handle this gracefully. **How precise is the location input for get_realtime_weather?** The system accepts four inputs: city name, zip code, latitude, or longitude. For maximum precision and reliable results, always pass specific lat/lon coordinates rather than relying on general place names. **Can I check both wildfire risk and air quality using get_wildfire_risk and get_air_quality_index?** You must call these tools separately for the required location and timeframe. Your agent executes each tool independently, then you merge those distinct data points in your code to create a comprehensive risk assessment. **Where do I retrieve my Tomorrow.io API Key?** Log into your account via `app.tomorrow.io`. Navigate directly to the **API Management** or Developer tab nested inside your settings. Create a new root token, copy it in its entirety, and insert it securely to enable queries. **How accurate is the 'minutely' precipitation forecast tool?** Tomorrow.io operates proprietary radar networks, satellites, and sophisticated high-resolution systems natively intended to provide powerful precision for up to exactly 60 minutes ahead, projecting precipitation downshifts incredibly well locally. **How far into the future can the agent forecast extreme weather events?** Using Tomorrow.io's advanced predictive modeling, the agent can provide precise hour-by-hour projections and daily forecasts up to 15 days ahead. This extended timeline offers ample opportunity for logistical and operational planning against severe environmental risks.