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