pvwatts-mcp
Enables solar energy potential assessment by converting parcel centroid and acreage into annual/monthly generation estimates using the NREL PVWatts v8 API, suitable for revenue modeling and infographic headlines.
README
pvwatts-mcp
MCP server wrapping NREL PVWatts v8 for the Watts for Water project. Turns a parcel centroid + acreage into annual / monthly generation estimates suitable for revenue modeling and infographic headline numbers.
See spec.md for the design doc.
Tools
| Tool | Purpose |
|---|---|
pvwatts_run |
Faithful wrapper around PVWatts v8. All parameters exposed; project defaults applied when omitted. |
solar_potential_for_acres |
Convenience: acreage + centroid → MW DC → annual MWh, capacity factor, indicative revenue. tracker=true flips to 1-axis backtracking. |
Setup
npm install
Get a free NREL API key at developer.nrel.gov/signup, then store it as a Worker secret:
npx wrangler secret put NREL_API_KEY
For local development with wrangler dev, put the same key in a .dev.vars file at the repo root (gitignored):
NREL_API_KEY=your-key-here
Running locally
npm run dev
Worker listens at http://localhost:8787. Test endpoints:
GET /— plain-text usage hintPOST /mcp— streamable HTTP transport (recommended)GET /sse— legacy SSE transport
Inspect with the MCP Inspector:
npx @modelcontextprotocol/inspector@latest
# Then open the URL it prints and connect to http://localhost:8787/mcp
Deploying
npx wrangler deploy
Then connect from Claude Desktop via mcp-remote:
{
"mcpServers": {
"pvwatts": {
"command": "npx",
"args": ["mcp-remote", "https://pvwatts-mcp.<your-account>.workers.dev/mcp"]
}
}
}
Acceptance test
The MCP is ready to ship when this call returns sane numbers:
// Tool: solar_potential_for_acres
{
"lat": 41.72,
"lon": -111.83, // Cache Valley, Utah
"acres": 80,
"tracker": false
}
Expected (per spec.md § Acceptance test, within ~10%):
system_capacity_mw_dc: 10.0annual.generation_mwh: 21,000 – 24,000annual.capacity_factor_pct: 24 – 26annual.indicative_revenue_usd: ~$735K – $840K at $35/MWh- Monthly trough in Dec/Jan (~1,000 MWh), peak in Jun/Jul (~2,400 MWh)
Re-running with tracker=true should bump annual generation to 25,000–28,000 MWh and capacity factor to ~28–30%, validating the array-type plumbing.
Layout
src/
index.ts Worker entrypoint — routes /mcp and /sse
mcp.ts McpAgent subclass; tool registrations
pvwatts.ts NREL adapter — fetch, retry, cache, error mapping
defaults.ts Utah utility-scale assumption set + caveat strings
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.