Solcast Solar MCP for AI. Predict PV output using precise site data.

Q: 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 lossfactor (system efficiency 0-1, default 0.9). If you don't know tilt/azimuth, Solcast will auto-estimate reasonable defaults based on your location.

Q: 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.

Q: 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.

Q: What is the difference between getsitemeasuredactuals and estimated production?

Use getsitemeasuredactuals 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.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

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.

What your AI can do

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.

+ 8 more capabilities included

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.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Solcast Solar: 11 Tools for PV Energy Forecasting

These tools allow your agent to calculate power output estimates and retrieve detailed solar resource data across various systems.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using Solcast Solar on Vinkius

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...

List Rooftop Sites

Lists all unique site IDs, capacities, and locations configured in your Solcast...

Get Pv Power Forecasts

Generates expected power output forecasts using satellite cloud tracking data for a...

Get Radiation Forecasts

Predicts raw solar irradiance metrics (GHI, DNI, DHI) needed for general solar...

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...

Get Site Measured Actuals

Pulls the exact measured PV power output from a registered, telemetry-enabled site...

Get Solar Summary

Combines irradiance, weather, and PV data into one overview for a complete solar...

Get Weather Forecasts

Predicts environmental factors like air temperature, cloud opacity, and snow depth...

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The Solcast Solar integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "solcast-solar": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the Solcast Solar tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"solcast-solar": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with Solcast Solar, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,100+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Solcast. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 11 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Figuring out solar output shouldn't require 15 clicks and three different logins.

Today, estimating a site’s power potential is painful. You jump between the climate modeling platform for general weather data; then you log into the asset management system to get the registered site ID; finally, you open an energy spreadsheet and manually input assumed tilt angles. It's slow, prone to copy-paste errors, and always requires manual validation against multiple dashboards.

With this MCP server, your agent handles the whole flow. You just ask it: 'What is the predicted output for my 5kW array?' The system runs `get_solar_summary` or `get_detailed_pv_forecast`, pulls in the weather context (`get_weather_forecasts`), and returns a single, validated number that accounts for everything.

Solcast Solar MCP Server: Get accurate power predictions.

Before this server, getting performance data required manually comparing the forecast model's output against the site inventory record. If you missed a single parameter—like whether the measurement was 'estimated' or 'measured'—the numbers were useless for auditing.

Now, your agent handles that nuance. You can call `get_site_estimated_actuals` versus `get_site_measured_actuals`. It instantly tells you if the number is a projection or hard data from the site’s telemetry feed. That difference matters.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

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.

Built · Hosted · Managed by Vinkius Solcast Solar MCP Server - PV Power Forecasts

Server ID 019d760a-e0d1-728c-accc-b1a8badb761a

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

Here's how it actually 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.

First, subscribe to the server and provide your Solcast API key. This connects the necessary solar resource models to your AI client.

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?'

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.

Who is this actually for?

Solar installers, grid operators, and energy traders rely on this daily. They hate guessing potential yield based on general weather reports; they need site-specific power models that account for panel orientation and historical data to guarantee bids or maintain the grid.

Solar Installer

Calculates accurate PV production estimates for clients, using get_detailed_pv_forecast when they know the exact tilt and azimuth. They use this to size systems correctly before the bid.

Grid Operator

Predicts distributed solar generation forecasts across multiple sites. They use list_rooftop_sites to track all connected assets and predict output for grid balancing.

Energy Trader

Integrates solar forecast data into energy trading models. They rely on get_solar_summary and get_weather_forecasts to predict supply peaks and manage dispatch planning.

Research Scientist

Validates academic models by retrieving historical solar irradiance data (get_historical_radiation) for specific time periods and locations.

What Changes When You Connect

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.

See it in action

01 01

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.

02 02

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.

03 03

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.

04 04

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.

The honest tradeoffs

Guessing Site ID

Anti-pattern

Trying to guess the correct site ID for a client's installation and running get_site_forecasts with a random string like 'xyz-123'. This will fail because the server needs an exact, registered ID.

The Fix

Always start by calling list_rooftop_sites. Once you have the official site ID from that list, then run any specific query using tools like get_site_forecasts or get_site_estimated_actuals.

Using General Weather for Output

Anti-pattern

Simply calling get_weather_forecasts and assuming the temperature or cloud opacity is enough to calculate power. This ignores the physical geometry of the panels.

The Fix

Use get_solar_summary. It takes weather data and location/capacity, combining it with PV physics calculations for a much more accurate output estimate.

Ignoring System Geometry

Anti-pattern

Running get_pv_power_forecasts when the system is known to be non-standard (e.g., tilted at 45°). This assumes default settings, leading to inaccurate numbers.

The Fix

When precision matters, use get_detailed_pv_forecast. It forces you to include the tilt and azimuth parameters for accurate modeling.

When It Fits, When It Doesn't

Use this server if your goal is to calculate a numerical estimate of electrical power (kW or kWh) based on solar physics. This includes project sizing, performance auditing, or resource assessment.

Don't use it if you just need general environmental data—for example, if you only want the average temperature for the week without knowing how panels react. For that, basic weather APIs might suffice. Also, if your primary goal is market trend analysis (e.g., predicting carbon prices), this solar tool won't help.

The key decision point is precision: If you have the panel tilt and azimuth angles, use get_detailed_pv_forecast. If you are only doing a quick feasibility check with minimal data, use get_simple_pv_forecast. Always cross-reference forecasts against measured actuals using get_site_measured_actuals if they exist—that's your ground truth.

Questions you might have

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.

Connect to your AI in seconds.

Get detailed pv forecast

Get historical radiation

List rooftop sites

Solcast Solar: 11 Tools for PV Energy Forecasting

Make your AI actually useful.

Get Detailed Pv Forecast

Get Historical Radiation

List Rooftop Sites

Get Pv Power Forecasts

Get Radiation Forecasts

Get Simple Pv Forecast

Get Site Estimated Actuals

Get Site Forecasts

Get Site Measured Actuals

Get Solar Summary

Get Weather Forecasts

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

Figuring out solar output shouldn't require 15 clicks and three different logins.

Solcast Solar MCP Server: Get accurate power predictions.

What your AI can actually do with this

Site Management and Quick Scopes

Modeling Known Sites (The Deep Dive)

Assessing Raw Resource Potential

Analyzing System Performance and History

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

Sizing a New Commercial Rooftop

Auditing a Flailing Site

Market Feasibility Study

Optimizing Charging Schedules

The honest tradeoffs

Guessing Site ID

Using General Weather for Output

Ignoring System Geometry

When It Fits, When It Doesn't

Questions you might have