# Solcast Solar MCP > Solcast Solar MCP Server predicts PV energy yield by connecting directly to high-resolution solar forecasting data. It gives you detailed, location-specific forecasts for rooftop solar systems, including power output (kW), Global Horizontal Irradiance (GHI), Direct Normal Irradiance (DNI), and local weather conditions. ## Overview - **Category:** the-unthinkable - **Price:** Free - **Tags:** solar-forecasting, irradiance-data, pv-power, satellite-data, renewable-energy, api-integration ## Description Solcast gives your agent deep solar forecasting intel. You're connecting directly to high-resolution data that tracks everything affecting a PV system, from satellite cloud movement to historical radiation records. ### Site Management and Quick Scopes Need to know what you're working with? Start by running `list_rooftop_sites`. This tool pulls all unique site IDs, capacities, and locations configured in your Solcast account. If you just need a quick estimate for an initial scoping call, use `get_simple_pv_forecast`. You only have to feed it latitude, longitude, and system capacity; that's all it needs. ### Modeling Known Sites (The Deep Dive) When you know the site, you get precise results. To model a known, registered rooftop array, use `get_site_forecasts`. This tool pulls power output predictions specifically tied to that site ID and its stored parameters. If you're trying to audit performance or predict yields when measured data isn't available, run `get_site_estimated_actuals` using the specific site ID. For maximum accuracy—the kind of detailed modeling that matters—you’ll want to use `get_detailed_pv_forecast`. This function requires you to input exact system geometry parameters like tilt and azimuth angle. That gives you the most accurate possible power output prediction. ### Assessing Raw Resource Potential Sometimes, you don't know the site yet; you just need to judge if a location is viable for solar. For that, you look at raw sunlight metrics using `get_radiation_forecasts`. This predicts core irradiance values: GHI, DNI, and DHI. You also get general resource assessment data with `get_solar_summary`, which combines irradiance, weather, and PV data into one full picture. If the area is broader and you just need to predict raw power output using satellite cloud tracking for a given site capacity, use `get_pv_power_forecasts`. ### Analyzing System Performance and History To check how things really are going, your agent can pull measured data. Running `get_site_measured_actuals` pulls the exact PV power output from any registered, telemetry-enabled site over time. For validating models or analyzing past performance trends, use `get_historical_radiation`. This retrieves years of actual solar irradiance readings (GHI, DNI, etc.) for a specific location and time range. You'll also need to factor in the environment. Use `get_weather_forecasts` to predict environmental factors like air temperature, cloud opacity, and snow depth—these things drastically affect your final output. For general resource assessment that combines everything into one view, run `get_solar_summary`. You can also get raw predictions for key irradiance metrics by calling `get_radiation_forecasts`. This toolkit lets you go from a quick estimate to a full-blown performance audit in minutes. ## Tools ### get_detailed_pv_forecast Calculates highly accurate PV power output using exact system geometry (tilt, azimuth) parameters. ### get_historical_radiation Retrieves past solar irradiance values (GHI, DNI, etc.) for a specific location and time range. ### list_rooftop_sites Lists all unique site IDs, capacities, and locations configured in your Solcast account. ### get_pv_power_forecasts Generates expected power output forecasts using satellite cloud tracking data for a given site capacity. ### get_radiation_forecasts Predicts raw solar irradiance metrics (GHI, DNI, DHI) needed for general solar resource assessment in an area. ### get_simple_pv_forecast Provides a fast PV power forecast using minimal inputs—just latitude, longitude, and system capacity. ### get_site_estimated_actuals Retrieves estimated recent PV output for a specific registered site ID when measured data isn't available. ### get_site_forecasts Predicts power output specifically for a known, registered rooftop site ID using its stored parameters. ### get_site_measured_actuals Pulls the exact measured PV power output from a registered, telemetry-enabled site over time. ### get_solar_summary Combines irradiance, weather, and PV data into one overview for a complete solar resource assessment. ### get_weather_forecasts Predicts environmental factors like air temperature, cloud opacity, and snow depth that affect solar output. ## Prompt Examples **Prompt:** ``` What is the solar forecast for my 5kW rooftop system in Sydney at -33.87, 151.21? ``` **Response:** ``` Fetching PV power forecasts... Your 5kW system in Sydney is forecast to generate approximately 18-22kWh today. Peak production will be between 11am-2pm with output reaching 3.8-4.2kW. Cloud cover is expected mid-afternoon, reducing output to ~2kW between 3-5pm. Tomorrow looks sunnier with estimated 24kWh total. ``` **Prompt:** ``` Show me the solar irradiance (GHI and DNI) forecast for my location at 34.05, -118.24. ``` **Response:** ``` Retrieving radiation forecasts... Los Angeles area (34.05, -118.24) shows strong solar irradiance today. Peak GHI reaches 850-920 W/m² around solar noon (12:30pm). DNI peaks at 780-850 W/m² under clear skies. Cloud opacity is low (10-15%) until late afternoon when increasing clouds may reduce DNI by 30-40%. Excellent conditions for solar generation. ``` **Prompt:** ``` How much solar energy will a 10kW system with south-facing panels (azimuth 180°, tilt 30°) generate tomorrow at latitude -37.81, longitude 144.96? ``` **Response:** ``` Getting detailed PV forecast... Your 10kW south-facing system in Melbourne (-37.81, 144.96) with 30° tilt is forecast to generate approximately 32-38kWh tomorrow. South orientation reduces output vs optimal north-facing in southern hemisphere. Peak output will be 5.5-6.5kW around 12-1pm. Morning and afternoon production will be moderate due to suboptimal azimuth. Daily total is about 15-20% lower than optimal north-facing configuration. ``` ## Capabilities ### Calculate Detailed PV Power Output You ask your agent to predict power output using specific angles (tilt/azimuth) and system size for maximum accuracy. ### Model System Performance with Site IDs The agent pulls forecasts or estimated actuals for a known, registered rooftop site ID. ### Assess Raw Solar Resource Potential You get the core sunlight metrics (GHI, DNI, DHI) needed to judge if a location is viable for solar power. ### Estimate Quick Power Yields The agent runs a fast forecast using only basic inputs like latitude, longitude, and system capacity. Good for initial scoping calls. ### Track System History & Weather Impacts You get data on measured production or concurrent weather forecasts (temperature, cloud opacity) to audit performance. ## Use Cases ### Sizing a New Commercial Rooftop A client has a building at 34.05, -118.24 and wants to know the maximum power output from a 10kW array. The agent calls `get_detailed_pv_forecast`, inputting the known tilt (e.g., 25°) and azimuth (e.g., 180°). The result gives them the precise, guaranteed kW estimate needed for the proposal. ### Auditing a Flailing Site The site owner suspects their system is underperforming. First, they call `list_rooftop_sites` to get the ID. Then, they run `get_site_measured_actuals` for that ID over 168 hours (one week) to see if the actual production matches historical expectations. ### Market Feasibility Study A developer is looking at a whole new area and needs to assess its solar potential before buying land. They use `get_radiation_forecasts` or `get_solar_summary` for the coordinates, confirming that GHI/DNI are high enough to justify the investment. ### Optimizing Charging Schedules An EV owner wants to charge their car using solar power. They ask for a forecast and the agent calls `get_pv_power_forecasts`. The resulting hourly kW output tells them exactly when they need to plug in to maximize green energy usage. ## Benefits - Accurate System Sizing: Use `get_detailed_pv_forecast` when you know the panel tilt and azimuth. This is how you guarantee a bid—it accounts for geometry, not just location. - Audit Performance: Compare what should have happened versus reality by calling `get_site_estimated_actuals` or `get_site_measured_actuals`. It shows if your system hit its targets. - Quick Scoping: Need a rough number fast? Use `get_simple_pv_forecast`. You only need to pass the latitude, longitude, and capacity. No geometry required. - Full Resource Picture: The `get_solar_summary` tool bundles irradiance, weather predictions, and PV estimates into one call. It’s better than running four different queries. - Understanding Limitations: Use `get_weather_forecasts` to check for cloud opacity or temperature drops before you even run the forecast. This lets you warn clients about expected reductions. ## How It Works The bottom line is: you tell your AI client what solar data you need—whether it's a quick estimate or historical proof—and it executes the necessary API calls to get the numbers. 1. First, subscribe to the server and provide your Solcast API key. This connects the necessary solar resource models to your AI client. 2. Next, prompt your agent with a specific requirement: 'I need an estimate for X kW at Y coordinates' or 'What was the historical GHI data for Z?' 3. Your agent selects the right tool (e.g., `get_detailed_pv_forecast`) and runs the query, returning raw power estimates, irradiance values, or weather metrics. ## Frequently Asked Questions **What parameters do I need to get a rooftop PV forecast?** At minimum, you need: **latitude**, **longitude**, and **system capacity (kW)**. For more accurate forecasts, also provide **tilt** (panel angle 0-90°), **azimuth** (panel direction 0°=north, 180°=south), and **loss_factor** (system efficiency 0-1, default ~0.9). If you don't know tilt/azimuth, Solcast will auto-estimate reasonable defaults based on your location. **How far ahead can Solcast forecast solar power?** Solcast provides forecasts from the present time up to **14 days ahead** (336 hours). Short-term forecasts (next 24-48 hours) are the most accurate, with accuracy gradually decreasing for longer horizons. Forecast data is available in 5-minute, 10-minute, 15-minute, 30-minute, or 60-minute intervals depending on your plan tier. **How do I get a Solcast API key and what does the free tier include?** Visit https://solcast.com/ and sign up for a free Developer API account. The free tier includes rooftop PV power forecasts with limited daily API calls. For production use with higher call volumes, historical data access, and advanced features, upgrade to Pro or Enterprise plans. Register at https://solcast.com/ to get your API key instantly. **What is the difference between GHI, DNI, and DHI?** **GHI (Global Horizontal Irradiance)** is the total solar radiation received on a horizontal surface. **DNI (Direct Normal Irradiance)** is the direct beam radiation received on a surface perpendicular to the sun. **DHI (Diffuse Horizontal Irradiance)** is the scattered radiation from the sky (not direct sunlight). GHI = DNI × cos(zenith angle) + DHI. For flat panels, GHI is most relevant. For tracking systems, DNI matters more. Cloudy conditions increase DHI proportion. **What is the difference between `get_site_measured_actuals` and estimated production?** Use `get_site_measured_actuals` when you need the exact physical output. This tool requires a site with real telemetry integration, giving you actual measured data instead of an estimate based on models. **How do I get a complete solar resource overview using `get_solar_summary`?** This tool combines irradiance forecasts (GHI/DNI/DHI), weather predictions, and PV output estimates into one call. It’s the best way to perform a full solar resource assessment for any location. **What's the difference between `get_simple_pv_forecast` and `get_detailed_pv_forecast`?** The simple forecast gives you a quick estimate using only latitude, longitude, and capacity. Use `get_detailed_pv_forecast` when you know specific system parameters like tilt, azimuth, or loss factor for higher accuracy. **What are the requirements for running `get_historical_radiation`?** You need a Pro or Enterprise plan to access full historical data. When calling this tool, ensure that your start and end dates are provided in ISO 8601 format.