# DeepPVMapper

> DeepPVMapper is an open-source MCP server for solar energy. Query 1.14 million French rooftop solar detections by area, capacity and year. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Open source
- **Platforms:** API, Web
- **Website:** https://deeppvmapper.fr
- **Repository:** https://github.com/gabrielkasmi/deeppvmapper/tree/HEAD/supabase/functions/mcp
- **MCP Registry name:** io.github.gabrielkasmi/deeppvmapper
- **Categories:** solar energy, analytics and data
- **Listing updated:** 2026-11-17

## About

DeepPVMapper is an open dataset of rooftop photovoltaic systems across France, produced by a deep-learning pipeline over IGN aerial imagery. The pipeline classifies image tiles with InceptionV3, segments positive patches, and extracts surface, tilt, azimuth and installed capacity for each detection. The site reports over 1.1 million systems and about 15 GWp of estimated capacity.

This public server exposes the detection registry over Streamable HTTP so an assistant can search detections, total installed capacity by département, explore an area, follow yearly deployment and check data-quality signals. No install is required; the endpoint is added as a custom connector.

The work comes from a PhD at Mines Paris-PSL, with model weights and the BDAPPV training dataset published on Hugging Face and Zenodo. Running the detection pipeline yourself needs GDAL and a GPU with at least 8 GB of VRAM.

## Features

- **Detection search:** Look up individual rooftop solar detections.
- **Capacity by département:** Aggregate estimated installed capacity per French département.
- **Area exploration:** Examine detections within a chosen area.
- **Yearly deployment:** Track how installations grew over time.
- **Data-quality signals:** Check indicators on how reliable the detections are.
- **Open pipeline:** Models, dataset and code are published for reuse.

## Good for

- Estimate rooftop solar capacity in a French département
- Chart how installations grew each year
- Check the reliability of detections in an area
- Cite an open dataset in solar research

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http deeppvmapper https://zelhliylrlktnasircwp.supabase.co/functions/v1/mcp/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://zelhliylrlktnasircwp.supabase.co/functions/v1/mcp/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "deeppvmapper": {
      "url": "https://zelhliylrlktnasircwp.supabase.co/functions/v1/mcp/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "deeppvmapper": {
      "type": "http",
      "url": "https://zelhliylrlktnasircwp.supabase.co/functions/v1/mcp/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "deeppvmapper": {
      "serverUrl": "https://zelhliylrlktnasircwp.supabase.co/functions/v1/mcp/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "deeppvmapper": {
      "type": "http",
      "url": "https://zelhliylrlktnasircwp.supabase.co/functions/v1/mcp/mcp"
    }
  }
}
```

## FAQ

### Does it need installing?

No. Add the endpoint as a custom connector in an MCP client.

### How large is the registry?

The README cites more than 1.14 million detections; the site shows 1.1M+ systems and 15.0 GWp estimated.

### Where is the data from?

IGN aerial imagery processed with deep-learning classification and segmentation.

### Can I run the pipeline myself?

Yes, it needs GDAL and a GPU with CUDA 11.8 or newer and 8 GB of VRAM.

### Is DeepPVMapper free?

Yes. DeepPVMapper is open source, so you can use and self-host it for free.

### How do I add DeepPVMapper to Claude Code?

Run this command in your terminal: claude mcp add --transport http deeppvmapper https://zelhliylrlktnasircwp.supabase.co/functions/v1/mcp/mcp

### What are the best alternatives to DeepPVMapper?

The closest alternatives to DeepPVMapper are Agent-Native Analytics, Google Ads + Meta Ads + SEO/GEO MCP, Tapetide - Indian Stock Market MCP, World Monitor and CompanyData.

## Alternatives

- [Agent-Native Analytics](https://ai-powered.com/mcp/agent-native-analytics): Agent-Native Analytics is an open-source MCP server for analytics and data.
- [Google Ads + Meta Ads + SEO/GEO MCP](https://ai-powered.com/mcp/google-ads-meta-ads-seo-geo-mcp): Google Ads + Meta Ads + SEO/GEO MCP is a freemium MCP server for marketing and seo.
- [Tapetide - Indian Stock Market MCP](https://ai-powered.com/mcp/tapetide-indian-stock-market-mcp): Tapetide - Indian Stock Market MCP is a freemium MCP server for finance and payments.
- [World Monitor](https://ai-powered.com/mcp/world-monitor): World Monitor is a freemium MCP server for analytics and data.
- [CompanyData](https://ai-powered.com/mcp/companydata): CompanyData is a paid MCP server for analytics and data.
- [ChartAnt](https://ai-powered.com/mcp/chartant): ChartAnt is a freemium MCP server for design and media.
- [Quantivex Research](https://ai-powered.com/mcp/quantivex-research): Quantivex Research is a free MCP server for finance and payments.
- [Provyan](https://ai-powered.com/mcp/provyan): Provyan is a free MCP server for finance and payments.

---
Source: https://ai-powered.com/mcp/deeppvmapper
