Solcast Solar MCP Server for Pydantic AI 11 tools — connect in under 2 minutes
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Solcast Solar through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP
async def main():
# Your Vinkius token — get it at cloud.vinkius.com
server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
agent = Agent(
model="openai:gpt-4o",
mcp_servers=[server],
system_prompt=(
"You are an assistant with access to Solcast Solar "
"(11 tools)."
),
)
result = await agent.run(
"What tools are available in Solcast Solar?"
)
print(result.data)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Solcast Solar MCP Server
Connect to Solcast API and bring high-resolution solar forecasting intelligence to any AI agent. Access rooftop PV power forecasts, solar irradiance data (GHI, DNI, DHI), and weather conditions derived from satellite cloud tracking worldwide.
Pydantic AI validates every Solcast Solar tool response against typed schemas, catching data inconsistencies at build time. Connect 11 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.
What you can do
- Rooftop PV Forecasts — Get PV power output forecasts (kW) for any rooftop solar system from present up to 14 days ahead
- Detailed PV Modeling — Forecast with exact system parameters (tilt, azimuth, capacity, loss factor) for maximum accuracy
- Solar Irradiance — Access GHI (Global Horizontal Irradiance), DNI (Direct Normal Irradiance), and DHI (Diffuse Horizontal Irradiance)
- Historical Radiation — Retrieve historical solar irradiance data for model validation and analysis
- Weather Forecasts — Get air temperature, cloud opacity, and snow depth data affecting solar production
- Site Management — List registered rooftop sites, get forecasts, estimated actuals, and measured production
- Quick Estimates — Get fast solar forecasts with minimal parameters (lat, lon, capacity only)
- Comprehensive Solar Summary — Combine irradiance, weather, and PV data in a single overview
The Solcast Solar MCP Server exposes 11 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Solcast Solar to Pydantic AI via MCP
Follow these steps to integrate the Solcast Solar MCP Server with Pydantic AI.
Install Pydantic AI
Run pip install pydantic-ai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save to agent.py and run: python agent.py
Explore tools
The agent discovers 11 tools from Solcast Solar with type-safe schemas
Why Use Pydantic AI with the Solcast Solar MCP Server
Pydantic AI provides unique advantages when paired with Solcast Solar through the Model Context Protocol.
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Solcast Solar integration code
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
Dependency injection system cleanly separates your Solcast Solar connection logic from agent behavior for testable, maintainable code
Solcast Solar + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the Solcast Solar MCP Server delivers measurable value.
Type-safe data pipelines: query Solcast Solar with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple Solcast Solar tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query Solcast Solar and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock Solcast Solar responses and write comprehensive agent tests
Solcast Solar MCP Tools for Pydantic AI (11)
These 11 tools become available when you connect Solcast Solar to Pydantic AI via MCP:
get_detailed_pv_forecast
Use when you know your system's exact configuration for maximum forecast accuracy. USE WHEN: - User knows exact panel tilt and azimuth angles - User needs highly accurate forecasts for a specific system - User has detailed PV system specifications - User asks for precise solar output estimates PARAMETERS: - latitude (REQUIRED): Location latitude - longitude (REQUIRED): Location longitude - capacity (REQUIRED): System capacity in kW - tilt (REQUIRED): Panel tilt angle in degrees - azimuth (REQUIRED): Panel azimuth in degrees - loss_factor (OPTIONAL): System loss factor (0-1, default: 0.9) EXAMPLES: - "Detailed forecast for 6kW system, tilt 30°, azimuth 0° (north facing)" → call with latitude, longitude, capacity=6, tilt=30, azimuth=0 - "Precise PV estimate for my 8kW array at 25° tilt, 180° azimuth (south)" → call with capacity=8, tilt=25, azimuth=180 Get detailed PV power forecast with full system specifications
get_historical_radiation
Requires Pro/Enterprise plan for full historical access. USE WHEN: - User asks about historical solar radiation data - User needs past solar irradiance values for analysis - User wants to validate solar models with historical data - User asks "what was the solar irradiance last week" PARAMETERS: - latitude (REQUIRED): Location latitude - longitude (REQUIRED): Location longitude - start (REQUIRED): Start date/time (ISO 8601 format) - end (OPTIONAL): End date/time (ISO 8601 format) EXAMPLES: - "Historical solar radiation for Sydney last week" → call with latitude=-33.87, longitude=151.21, start="2026-03-31" - "GHI data for my location for March 2026" → call with latitude, longitude, start="2026-03-01", end="2026-03-31" Get historical solar irradiance data for a location
get_pv_power_forecasts
Forecasts are derived from satellite cloud tracking and irradiance data. USE WHEN: - User asks about solar power generation forecasts - User needs PV output estimates for a specific location - User wants to know expected solar energy production - User asks "how much solar power will my panels generate" PARAMETERS: - latitude (REQUIRED): Location latitude (-90 to 90) - longitude (REQUIRED): Location longitude (-180 to 180) - capacity (REQUIRED): System capacity in kW (DC rating) - tilt (OPTIONAL): Panel tilt angle in degrees (0=flat, 90=vertical) - azimuth (OPTIONAL): Panel azimuth in degrees (0=north, 180=south) - hours (OPTIONAL): Number of hours to forecast (default: 48, max: 336 for 14 days) EXAMPLES: - "Solar forecast for my 5kW system in Sydney -33.87, 151.21" → call with latitude=-33.87, longitude=151.21, capacity=5 - "PV forecast for 10kW rooftop in LA 34.05, -118.24" → call with latitude=34.05, longitude=-118.24, capacity=10 - "How much solar will my 3kW system generate tomorrow?" → call with latitude, longitude, capacity=3, hours=24 Get rooftop PV power forecasts for a location
get_radiation_forecasts
Essential for solar resource assessment. USE WHEN: - User asks about solar irradiance or solar radiation - User needs GHI, DNI, or DHI data for solar analysis - User is evaluating solar potential for a location - User asks "how much sunlight will there be" PARAMETERS: - latitude (REQUIRED): Location latitude - longitude (REQUIRED): Location longitude - hours (OPTIONAL): Number of hours to forecast (default: 48) EXAMPLES: - "Solar irradiance forecast for Sydney -33.87, 151.21" → call with latitude=-33.87, longitude=151.21 - "GHI and DNI forecast for my location 34.05, -118.24" → call with latitude=34.05, longitude=-118.24 - "How much solar radiation tomorrow?" → call with latitude, longitude, hours=24 Get solar irradiance forecasts (GHI, DNI, DHI) for a location
get_simple_pv_forecast
The API auto-estimates tilt and azimuth for reasonable default values. Perfect for quick estimates. USE WHEN: - User wants a quick solar estimate without exact system details - User doesn't know their panel tilt or azimuth - User needs a fast solar output estimate - User asks "roughly how much solar will I generate" PARAMETERS: - latitude (REQUIRED): Location latitude - longitude (REQUIRED): Location longitude - capacity (REQUIRED): System capacity in kW EXAMPLES: - "Quick solar estimate for -33.87, 151.21 with 5kW" → call with latitude=-33.87, longitude=151.21, capacity=5 - "Rough estimate for my 3kW system in LA" → call with latitude=34.05, longitude=-118.24, capacity=3 - "How much solar for a 10kW system here?" → call with latitude, longitude, capacity=10 Get quick PV power forecast with minimal parameters
get_site_estimated_actuals
Shows what your system likely produced recently. USE WHEN: - User wants to know what their solar system actually generated - User needs recent production estimates vs forecasts - User is analyzing system performance - User asks "how much did my solar panels actually produce" PARAMETERS: - site_id (REQUIRED): The site ID from your Solcast account - hours (OPTIONAL): Number of hours of historical data (default: 24) EXAMPLES: - "Estimated actuals for site abc-123 last 24 hours" → call with site_id="abc-123" - "What did my system produce yesterday?" → call with site_id="abc-123", hours=48 - "Recent solar production for my site" → call with site_id="your-site-id" Get estimated actual PV power output for a registered rooftop site
get_site_forecasts
Uses the site's configured parameters (capacity, tilt, azimuth) for accurate forecasts. USE WHEN: - User asks about forecasts for a specific registered site - User has a site ID and wants forecasts for that system - User needs predictions for a known rooftop installation - User asks "what will my registered solar site generate" PARAMETERS: - site_id (REQUIRED): The site ID from your Solcast account EXAMPLES: - "Forecast for site abc-123" → call with site_id="abc-123" - "What will my registered system def-456 generate?" → call with site_id="def-456" - "Solar forecast for my home system" → call with site_id="your-site-id" Get PV power forecasts for a specific registered rooftop site
get_site_measured_actuals
Requires the site to have real measurement integration. Shows exact production data. USE WHEN: - User has telemetry-enabled sites with real measurements - User needs exact measured production data (not estimates) - User is validating forecast accuracy - User asks "what was the exact measured output from my system" PARAMETERS: - site_id (REQUIRED): The site ID with telemetry enabled - hours (OPTIONAL): Number of hours of historical data EXAMPLES: - "Measured actuals for telemetry site xyz-789" → call with site_id="xyz-789" - "Exact production from my monitored system" → call with site_id="your-telemetry-site-id" - "Real production data last week" → call with site_id="xyz-789", hours=168 Get measured PV power output from a registered rooftop site with telemetry
get_solar_summary
Provides a complete picture of solar resources. USE WHEN: - User wants a complete solar overview for a location - User needs both irradiance and PV forecasts together - User asks for a solar resource assessment - User wants "complete solar data for my area" PARAMETERS: - latitude (REQUIRED): Location latitude - longitude (REQUIRED): Location longitude - capacity (OPTIONAL): System capacity in kW (for PV estimates) EXAMPLES: - "Complete solar summary for Sydney -33.87, 151.21" → call with latitude=-33.87, longitude=151.21 - "Solar resource assessment for my location 34.05, -118.24" → call with latitude=34.05, longitude=-118.24 - "Full solar data with 5kW system estimate" → call with latitude, longitude, capacity=5 Get a comprehensive solar summary including irradiance, weather, and PV forecasts
get_weather_forecasts
Useful for understanding conditions affecting solar output. USE WHEN: - User asks about weather conditions affecting solar panels - User needs temperature or cloud cover forecasts - User wants to understand weather impact on solar generation - User asks "what's the weather forecast for solar" PARAMETERS: - latitude (REQUIRED): Location latitude - longitude (REQUIRED): Location longitude - hours (OPTIONAL): Number of hours to forecast EXAMPLES: - "Weather forecast for solar panels in Sydney -33.87, 151.21" → call with latitude=-33.87, longitude=151.21 - "Cloud cover forecast for my location 34.05, -118.24" → call with latitude=34.05, longitude=-118.24 - "Temperature forecast for next week" → call with latitude, longitude, hours=168 Get weather forecasts including temperature, cloud opacity, and snow depth
list_rooftop_sites
Shows site IDs, capacities, and locations for managing multiple solar installations. USE WHEN: - User wants to see all their registered solar sites - User needs to find site IDs for other queries - User is managing multiple rooftop installations - User asks "what solar sites do I have configured" EXAMPLES: - "List all my solar sites" → call with no params - "Show my registered rooftop PV systems" → call with no params - "What sites do I have in Solcast?" → call with no params List all configured rooftop PV sites in your Solcast account
Example Prompts for Solcast Solar in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with Solcast Solar immediately.
"What is the solar forecast for my 5kW rooftop system in Sydney at -33.87, 151.21?"
"Show me the solar irradiance (GHI and DNI) forecast for my location at 34.05, -118.24."
"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?"
Troubleshooting Solcast Solar MCP Server with Pydantic AI
Common issues when connecting Solcast Solar to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiSolcast Solar + Pydantic AI FAQ
Common questions about integrating Solcast Solar MCP Server with Pydantic AI.
How does Pydantic AI discover MCP tools?
MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.Does Pydantic AI validate MCP tool responses?
Can I switch LLM providers without changing MCP code?
Connect Solcast Solar with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Solcast Solar to Pydantic AI
Get your token, paste the configuration, and start using 11 tools in under 2 minutes. No API key management needed.