- DATA
- SEARCH
- MAP
- HUMAN
Short answer
How can I find specific satellite scenes with my AI?
Your AI uses spatial coordinates or MGRS tiles to scan the Sentinel Hub catalog for matching imagery. Once found, it pulls the specific metadata for those scenes so you can inspect cloud cover, timestamps, or sensor types. You get a filtered list of available data.
The results.
Where your queries land.
The AI translates your location-based requests into specific data outputs.
DATA
Metadata lists
The AI pulls specific scene properties like acquisition time and cloud cover. You get a clean summary of what's available in your target area.
SEARCH
Filtered catalogs
Instead of browsing a web portal, your agent filters the entire Sentinel Hub catalog based on your exact spatial constraints.
MAP
Tile-based results
Request data for specific MGRS tiles to get a focused set of imagery. The AI maps your request to the correct grid cells automatically.
HUMAN
Manual inspection
The AI identifies the best scenes, but you decide which specific images are high-quality enough for your final analysis.
The workflow
What your AI does when a request arrives.
The AI acts as the bridge between your chat interface and the Sentinel Hub database.
Locate imagery
The agent scans the available satellite collections to find scenes that match your requested area or grid.
catalog_searchTarget specific tiles
If you provide a specific MGRS tile, the AI narrows the search to that exact geographic footprint.
search_by_tileExtract properties
The AI pulls the technical metadata for a specific scene to check if it meets your requirements.
get_catalog_itemSummarize findings
The agent presents the relevant scene details in your chat, highlighting the most useful metadata points.
get_catalog_item
Try it
Copy these to start.
Use these prompts to trigger the Sentinel Hub tools.
Starting points
Swap the bracketed text for your actual coordinates, MGRS tiles, or specific sensor interests.
Sentinel Hub Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_xyVUwa3x77fWINQTr8feR7dKZks5UVMkLVCjWXd2/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Sentinel Hub capabilities are ready to use.
{
"mcpServers": {
"sentinel-hub-mcp": {
"url": "https://edge.vinkius.com/vk_preview_xyVUwa3x77fWINQTr8feR7dKZks5UVMkLVCjWXd2/mcp"
}
}
}Find all Sentinel-2 scenes in the area around [insert coordinates] with low cloud cover.
Search for available imagery within the MGRS tile [insert tile ID].
Get the metadata for the most recent satellite scene in [insert region].
List the available satellite products in the catalog that cover [insert location].
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Sentinel Hub once, then ask.
One click connects the MCP to your client. Your credentials stay encrypted and secure, and you can immediately start querying imagery.
Connect Sentinel Hub to your AIFAQ
How this task behaves.
- 01
Can the AI download the actual image files?
No. The AI can only search the catalog and retrieve metadata properties for the scenes.
- 02
Can I use MGRS tiles for searching?
Yes. The AI can search specifically by MGRS tile to find relevant imagery.
- 03
Will the AI change my Sentinel Hub settings?
No. The AI only reads data from the catalog; it cannot modify your account or configuration.
- 04
Can the AI filter by cloud cover percentage?
Yes. You can ask the AI to find scenes with specific cloud cover limits using the catalog search.
- 05
Does the AI perform the image processing?
No. The AI finds the data and reads the metadata, but the actual image analysis or processing is done by you or your other tools.
More questions about Sentinel Hub? The Connector page answers them. See everything the Sentinel Hub Connector can do
Connect Sentinel Hub to Claude, Cursor, ChatGPT & more
