Solar MCP

Solar MCP

An MCP server that enables AI assistants to look up solar permitting authorities, estimate solar production via PVWatts, and retrieve irradiance data. It streamlines the creation of solar-aware workflows by integrating industry-standard APIs like NREL.

Category
访问服务器

README

License: MIT

Solar MCP

A community-sponsored open-source MCP server that wraps solar industry APIs as tools for AI assistants. Built with FastMCP and hosted as a public endpoint at api.ontologic.co/solar-mcp.

Solar MCP gives AI assistants the ability to look up permitting authorities, estimate solar production, and retrieve solar resource data — making it easy to build solar-aware AI workflows.


Available Tools

lookup_ahj

Look up the Authority Having Jurisdiction (AHJ) for a solar installation site.

Parameter Type Required Description
address string One of address or lat/lon Street address
lat float One of address or lat/lon Latitude
lon float One of address or lat/lon Longitude

Returns: ahj_name, ahj_id, building_code, electrical_code, fire_code, permit_authority, inspection_body, contact_name, contact_email, contact_phone, website

lookup_ahj_requirements

Look up detailed permitting requirements for a specific AHJ.

Parameter Type Required Description
ahj_id string Yes AHJ ID from lookup_ahj

Returns: nec_version, ibc_version, irc_version, special_requirements (list), permit_process_notes, online_submission (bool), typical_turnaround_days

lookup_pvwatts

Get a PVWatts v8 solar production estimate.

Parameter Type Required Default Description
address string One of address or lat/lon — Street address
lat float One of address or lat/lon — Latitude
lon float One of address or lat/lon — Longitude
system_capacity_kw float Yes — System size in kW
tilt float No 20 Panel tilt angle
azimuth float No 180 Panel azimuth (180 = south)
array_type int No 1 0=fixed ground, 1=fixed open rack, 2=1-axis, 3=1-axis backtrack, 4=2-axis
module_type int No 0 0=standard, 1=premium, 2=thin film
losses float No 14 System losses (%)

Returns: ac_annual_kwh, ac_monthly_kwh (12 values), solrad_annual, capacity_factor, station_info

lookup_solar_resource

Get solar resource data (irradiance) for a location.

Parameter Type Required Description
address string One of address or lat/lon Street address
lat float One of address or lat/lon Latitude
lon float One of address or lat/lon Longitude

Returns: avg_dni, avg_ghi, avg_lat_tilt, nearest_station_name, station_distance_miles


Connect in Claude Desktop

Add this to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "solar-mcp": {
      "url": "https://api.ontologic.co/solar-mcp/mcp"
    }
  }
}

Or to run locally:

{
  "mcpServers": {
    "solar-mcp": {
      "url": "http://localhost:8000/solar-mcp/mcp"
    }
  }
}

Run Locally

With Docker

docker build -t solar-mcp .
docker run -p 8000:8000 \
  -e NREL_API_KEY=your_key_here \
  -e SUNSPEC_API_TOKEN=your_token_here \
  solar-mcp

Without Docker

pip install -e ".[dev]"
cp .env.example .env
# Edit .env with your API keys
python server.py

Environment Variables

Variable Required Description
NREL_API_KEY Yes NREL API key (get one free)
SUNSPEC_API_TOKEN No SunSpec AHJ Registry token (mock data used until available)
PORT No Server port (default: 8000)

Running Tests

pip install -e ".[dev]"
pytest tests/ -v

Attribution

  • NREL — PVWatts v8 API and Solar Resource Data API. This tool uses the NREL Developer Network API but is not endorsed or certified by NREL.
  • SunSpec Alliance — AHJ Registry API. AHJ data is currently mocked based on publicly available information; real API integration is pending token access.

Contributing

Contributions are welcome! To add a new tool:

  1. Add Pydantic schemas in models/schemas.py
  2. Add a client in clients/ (keep API interaction separate from tool logic)
  3. Add the tool function in tools/
  4. Register the tool in server.py
  5. Add tests in tests/
  6. Update this README

Please open an issue first to discuss new tools or significant changes.


License

MIT

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选