# Umbra open SAR archive

> Umbra open SAR archive is an open-source MCP server for analytics and data. Search, preview and measure Umbra's open SAR satellite imagery from an AI client. It can run locally on your machine or as a hosted remote server.

- **Kind:** MCP server
- **Pricing:** Open source
- **Platforms:** API, CLI, self-hosted
- **Repository:** https://github.com/reesehammer/umbra-py
- **MCP Registry name:** io.github.reesehammer/umbra-mcp
- **Categories:** [analytics and data](https://ai-powered.com/categories/analytics-and-data), [maps and travel](https://ai-powered.com/categories/maps-and-travel)
- **Listing updated:** 2026-11-18

## About

Umbra publishes 16 to 25 cm SAR under CC BY 4.0 but offers no search API, only a bucket of more than 17 TB and a static STAC tree. The umbra-py project fills that gap with search by bounding box, place name, polygon or Umbra task, plus previews, downloads and analysis-ready arrays. The MCP server sits on the same host as a community STAC API, so an assistant can query the archive with nothing installed.

Product types differ in what they are good for: GEC is the map-ready geocoded GeoTIFF to start with, while SICD and CPHD are complex products to download rather than convert. The converter turns a SICD into an amplitude COG and discards phase, so this is not an InSAR toolbox. Calibration options refuse to run rather than invent numbers for products without radiometric metadata.

The hosted API is best-effort at 99% monthly uptime with no SLA, 120 requests a minute and a page size of 10,000. Setting a Canopy token points the same tools at Umbra's authenticated commercial archive. The project is not affiliated with Umbra Lab, Inc.

## Features

- **Archive search:** Find scenes by area, bbox, polygon or task name across the open bucket.
- **Previews without download:** Quicklooks, galleries and tile views avoid pulling multi-gigabyte scenes.
- **Loading and conversion:** Load GEC into xarray or GeoTIFF, or convert a SICD to a geocoded amplitude COG.
- **ML chips:** Cut georeferenced tiles for super-resolution or target-recognition benchmarks.
- **Remote MCP and STAC API:** A hosted endpoint works with Claude and pystac-client with no install.
- **Attribution stamped:** Outputs carry the CC BY 4.0 data notice.

## Good for

- Find recent Umbra scenes over a named place
- Preview a scene before downloading it
- Build a chipped training set from open GEC or SICD products
- Replace a crawler of the Umbra S3 bucket with a STAC query
- Stream a downsampled window into xarray for analysis

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http umbra-mcp https://api.umbra-py.space/mcp
```

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

```sh
https://api.umbra-py.space/mcp
```

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

```json
{
  "mcpServers": {
    "umbra-mcp": {
      "url": "https://api.umbra-py.space/mcp"
    }
  }
}
```

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

```json
{
  "servers": {
    "umbra-mcp": {
      "type": "http",
      "url": "https://api.umbra-py.space/mcp"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "umbra-mcp": {
      "serverUrl": "https://api.umbra-py.space/mcp"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "umbra-mcp": {
      "type": "http",
      "url": "https://api.umbra-py.space/mcp"
    }
  }
}
```

## FAQ

### Is the data free to use?

The imagery is CC BY 4.0, so you must attribute Umbra; umbra-py itself is Apache 2.0.

### Does it do InSAR?

No. Phase is not preserved when converting, and it does not form interferograms or compute coherence.

### What are the hosted limits?

Best-effort 99% monthly uptime with no SLA, 120 requests per minute and a page size of 10,000.

### How do I use the commercial archive?

Set the Canopy API token and the same tools query the authenticated archive.

### Is it affiliated with Umbra?

No.

### Is Umbra open SAR archive free?

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

### How do I add Umbra open SAR archive to Claude Code?

Run this command in your terminal: claude mcp add --transport http umbra-mcp https://api.umbra-py.space/mcp

### What are the best alternatives to Umbra open SAR archive?

The closest alternatives to Umbra open SAR archive are Agent-Native Analytics, Google Ads + Meta Ads + SEO/GEO MCP, dashboard-icons, Tapetide - Indian Stock Market MCP and Atli.

## Where this comes from

- Description: written from the project's README.
- Install steps: from the official MCP Registry entry.

## 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.
- [dashboard-icons](https://ai-powered.com/mcp/dashboard-icons): dashboard-icons is an open-source MCP server for analytics and data.
- [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.
- [Atli](https://ai-powered.com/mcp/atli): Atli is a free MCP server for maps and travel.
- [World Monitor](https://ai-powered.com/mcp/world-monitor): World Monitor is a freemium MCP server for analytics and data.
- [CAD2GIS](https://ai-powered.com/mcp/cad2gis): CAD2GIS is an open-source MCP server for engineering simulation.
- [DataArcus for Power BI](https://ai-powered.com/mcp/dataarcus-for-power-bi): DataArcus for Power BI is a free MCP server for analytics and data.

---
Source: https://ai-powered.com/mcp/umbra-open-sar-archive
