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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。