MCP For Claude Marketplace
Sentinel Hub

Sentinel Hub MCP Connector for Claude

A+

Access and process satellite imagery from Sentinel, Landsat, and other Earth observation missions through a powerful cloud API.

14 tools Official Updated Jun 28, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect to Sentinel Hub — the most powerful satellite imagery processing API in Europe — and transform raw Earth observation data into actionable intelligence.

What you can do

  • STAC Catalog Search — Discover available satellite scenes by location, date, collection, cloud cover, and MGRS tile ID across all Sentinel missions and Landsat
  • Image Processing — Render custom satellite imagery using evalscripts (JavaScript-based processing scripts) that define how bands are combined, indices are calculated, and pixels are colored
  • Vegetation Analysis (NDVI) — Generate ready-to-use NDVI evalscripts that color-code vegetation density from bare soil to dense forest
  • Statistical Analysis — Calculate mean, min, max, standard deviation, and histograms over areas of interest with temporal aggregation (daily, weekly, monthly)
  • Cloud-Free Search — Find satellite scenes below a specified cloud cover threshold for clean optical analysis
  • Band Combinations — Access a curated library of 10 predefined band combinations including True Color, False Color, NDWI, Moisture Index, SWIR, and Burn Severity

How it works

  1. Subscribe to this server
  2. Register at dataspace.copernicus.eu and create an OAuth2 client
  3. Enter your credentials as client_id:client_secret
  4. Start processing satellite imagery from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • GIS Professionals — process satellite imagery on-demand without downloading terabytes of raw data
  • Environmental Scientists — compute vegetation, water, and moisture indices for monitoring ecosystems
  • Urban Planners — analyze land use changes with multi-temporal statistical analysis
  • Agricultural Advisors — monitor crop health with NDVI time series and cloud-free imagery selection
  • Emergency Managers — assess wildfire damage with burn severity indices in near real-time
satellite-imageryearth-observationgeospatial-datastacremote-sensingraster-processing

14 tools expose this connector's capabilities to your AI agent.

catalog_search

Specify a collection ID (e.g., "sentinel-2-l2a", "sentinel-1-grd"), a bounding box as [west, south, east, north] coordinates, and a date range. Returns item metadata including geometry, cloud cover, and band information. Search the Sentinel Hub STAC catalog for satellite imagery

check_sentinel_hub_status

Returns the connection status and service URL. Use this to verify your client_id:client_secret credentials are working correctly. Verify Sentinel Hub API connectivity and authentication

generate_false_color_evalscript

In the output, healthy vegetation appears bright red, urban areas appear cyan/grey, and water appears dark blue. This is the standard false-color composite used in remote sensing for vegetation mapping and land cover classification. Generate a false-color evalscript for vegetation emphasis

generate_ndvi_evalscript

The output is color-coded: dark for water/shadow, grey for bare soil, yellow-green for sparse vegetation, and deep green for dense vegetation. Use the returned evalscript with the process_image tool. Generate a ready-to-use NDVI evalscript for vegetation analysis

generate_true_color_evalscript

Use the returned evalscript with the process_image tool to get visually appealing satellite photos of any location on Earth. Generate a true-color RGB evalscript for natural imagery

get_catalog_collection

Get detailed information about a specific data collection

get_catalog_item

Use the item ID returned from a catalog_search query. Get detailed metadata for a specific STAC catalog item

get_statistics

Requires an evalscript that defines which bands to analyze. Supports temporal aggregation (daily, weekly, monthly) for time-series analysis of vegetation indices, water levels, or urban expansion. Calculate statistics over an area from satellite imagery

get_user_info

Useful for verifying credentials and understanding available quotas. Get authenticated Sentinel Hub user profile information

list_band_combinations

Includes True Color, False Color (vegetation), NDVI, NDWI, Moisture Index, SWIR, SAR polarizations, Scene Classification, and Burn Severity (NBR). Each entry specifies the required bands and target collection. List predefined satellite band combinations and indices

list_catalog_collections

Includes Sentinel-1 GRD (radar), Sentinel-2 L1C/L2A (optical), Sentinel-3 OLCI/SLSTR, Sentinel-5P (atmosphere), Landsat 8-9, DEM, and Copernicus Land Monitoring Service data. List all available Sentinel Hub satellite data collections

process_image

Specify the data collection, area of interest as a bounding box, date range, and the evalscript. The evalscript defines band inputs, processing logic, and output format. Use generate_ndvi_evalscript or generate_true_color_evalscript tools to get ready-made evalscripts. Process satellite imagery with a custom evalscript

search_by_tile

MGRS tiles are the standard spatial reference for Sentinel-2 data (e.g., "33UUP" for central Europe, "29SQB" for Lisbon area). Returns all scenes for the specified tile within the date range. Search Sentinel-2 imagery by MGRS tile identifier

search_cloud_free

Essential for optical analysis where cloud contamination would corrupt results. Typical thresholds: <10% for clean analysis, <30% for general use, <50% for temporal coverage. Search for cloud-free satellite imagery below a threshold

See how to talk to your AI agent using Sentinel Hub.

Show me an NDVI vegetation analysis for the Amazon rainforest region.

I'll start by generating the NDVI evalscript... Done. Now processing Sentinel-2 imagery for the Amazon basin (-65,-5,-55,0) from the last 30 days. The processed result shows a 512x512 pixel NDVI map with dense vegetation (deep green) covering 87% of the area, sparse vegetation (yellow-green) at 8%, and water bodies (dark) at 5%. Would you like time-series statistics to track deforestation trends?

Find cloud-free Sentinel-2 imagery over Paris with less than 10% clouds.

Searching for cloud-free scenes over Paris (2.2,48.8,2.5,48.9) with maximum 10% cloud cover... Found 3 scenes from the last month. The cleanest acquisition has 2.1% cloud cover from 5 days ago, captured by Sentinel-2A. The next scene has 7.3% from 10 days ago. Would you like me to generate a true-color image of the cleanest scene?

What band combinations can I use for wildfire assessment?

I've listed the available band combinations. For wildfire assessment, you should use the **Burn Severity (NBR)** index which combines bands B08 (NIR) and B12 (SWIR) from Sentinel-2. For broader context, the **SWIR** composite (B12, B8A, B04) highlights burned areas in distinctive colors. The **False Color (Vegetation)** combination (B08, B04, B03) also clearly distinguishes healthy vegetation from burned areas. Would you like me to process burn severity for a specific region?

An evalscript is a small JavaScript program that tells Sentinel Hub how to process satellite bands into an output image. It defines which bands to use, how to combine them, and what colors to assign. You can use the generate_ndvi_evalscript or generate_true_color_evalscript tools to get ready-made evalscripts, then pass them to the process_image tool.

Related Connectors

CO

Convertlab MCP

8 tools Official

Marketing automation and customer data platform — manage customers, campaigns, and events via AI.

A+ View details →
SF

Simple Fatoora MCP

11 tools Official

Generate ZATCA-compliant electronic invoices for Saudi Arabian businesses with automated tax calculations and QR code embedding.

A+ View details →
WS

Watchmode Streaming Availability MCP

8 tools Official

Find where to watch any movie or TV show — search streaming availability across Netflix, Disney+, HBO Max, and 200+ platforms directly from your AI agent.

A+ View details →
AN

Anthropic MCP

8 tools Official

Interact with Claude models via the Anthropic Messages API — send prompts, manage batches, and monitor rate limits directly.

A View details →