How do I use this MCP with Claude or Cursor?

Once you subscribe on Vinkius and provide your Sentinel Hub credentials, you simply connect your client to the Vinkius host. Your AI client will then see the available capabilities automatically.

What satellite missions can I access?

You can access data from Sentinel-1, Sentinel-2, Sentinel-3, Sentinel-5P, Landsat 8-9, and various Copernicus Land Monitoring services.

Do I need to write my own JavaScript for image processing?

No. The MCP includes capabilities to generate ready-to-use evalscripts for common tasks like NDVI, True Color, and False Color imagery.

Can I search for images without clouds?

Yes. The search_cloud_free capability allows you to specify a cloud cover threshold to ensure you get clean optical data.

Is it possible to perform statistical analysis over time?

Yes. The get_statistics capability supports temporal aggregation, allowing you to calculate mean, min, or max values over daily, weekly, or monthly periods.

What is an evalscript and how do I use one?

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 capabilities to get ready-made evalscripts, then pass them to the process_image capability.

Can I analyze vegetation health with this server?

Absolutely. Generate an NDVI evalscript with the generate_ndvi_evalscript capability, then process imagery for your area of interest with the process_image capability. For time-series analysis, use the get_statistics capability with temporal aggregation to track vegetation changes over weeks or months. The search_cloud_free capability helps you find clean scenes without cloud contamination.

What is the difference between this server and the Copernicus Data Space server?

The Copernicus Data Space server focuses on product catalogue search and download. finding and retrieving raw satellite data files. Sentinel Hub focuses on on-the-fly processing. rendering images, computing indices, and generating statistics without downloading raw data. They complement each other: use Copernicus for data discovery and bulk download, Sentinel Hub for real-time analysis and visualization.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Sentinel Hub to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Turn raw Earth observation data into actionable spatial intelligence.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 14 capabilities

We ship only the actions that matter.

Capability set01 / 04

01-04

4 capabilities in this set.

Part of 14 available through Sentinel Hub.

01
Check sentinel hub status
Verifies your connection and credentials. Use this to confirm your client_id and client_secret are working.
02
Generate false color evalscript
Creates a false-color composite script. This highlights healthy vegetation in red and water in dark blue for land cover classification.
03
Generate ndvi evalscript
Produces an NDVI evalscript for vegetation analysis. The output uses color coding to show everything from bare soil to dense forest.
04
Generate true color evalscript
Generates a true-color RGB evalscript. Use this to get natural-looking satellite photos of any location.

Capability set02 / 04

05-08

4 capabilities in this set.

Part of 14 available through Sentinel Hub.

05
Get user info
Retrieves your authenticated profile. It is the best way to check your available usage quotas.
06
List band combinations
Lists all predefined band combinations. This includes NDVI, NDWI, Moisture Index, and Burn Severity.
07
Search by tile
Searches for imagery using MGRS tile identifiers. This returns all available scenes for a specific tile within your date range.
08
Catalog search
Queries the STAC catalog using bounding boxes and collection IDs. It returns metadata like geometry and cloud cover.

Capability set03 / 04

09-11

3 capabilities in this set.

Part of 14 available through Sentinel Hub.

09
Get catalog collection
Fetches detailed information about a specific data collection.
10
Get catalog item
Retrieves specific metadata for a single STAC catalog item using its ID.
11
Get statistics
Calculates statistical values over a defined area. It supports temporal aggregation for tracking changes over days, weeks, or months.

Capability set04 / 04

12-14

3 capabilities in this set.

Part of 14 available through Sentinel Hub.

12
List catalog collections
Shows all available data collections, including Sentinel-1, Sentinel-2, Landsat, and Copernicus Land Monitoring Service.
13
Process image
Renders satellite imagery using a custom evalscript. You provide the bounding box, date range, and the processing logic.
14
Search cloud free
Filters the catalog for scenes with low cloud cover. This is vital for clean optical analysis.

Real work

What teams actually run

Deforestation Tracking

Use NDVI time series to monitor changes in forest density over months or years.

Wildfire Damage Assessment

Apply burn severity indices to evaluate the impact of fires on specific regions.

Urban Expansion Analysis

Run statistical analysis on land use changes using multi-temporal data.

Water Resource Monitoring

Calculate moisture indices to track water levels and soil conditions.

Automate a task

Put Sentinel Hub to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Sentinel Hub works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Sentinel Hub to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

913ms average. Fast in production.

Sentinel Hub is checked daily against the live service.

Daily averagePeak 1293ms

Oct 3Today

Fastest day: 784ms
Slowest day: 1293ms
14-day trend: Slowing+6%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 14 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Sentinel Hub, so you can see the experience inside your AI.

It does not authenticate your account with Sentinel Hub. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Sentinel Hub Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_xyVUwa3x77fWINQTr8feR7dKZks5UVMkLVCjWXd2/mcp

Claude 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.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "sentinel-hub-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_xyVUwa3x77fWINQTr8feR7dKZks5UVMkLVCjWXd2/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Sentinel Hub in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Sentinel Hub owners hand off.

This MCP is built for professionals working with geospatial and environmental data who need to bypass manual data downloading.

01
GIS Professionals
They use the AI to process imagery on-demand without managing massive local datasets.
02
Environmental Scientists
They hand off the task of computing vegetation and moisture indices to the agent.
03
Agricultural Advisors
They use the AI to monitor crop health via NDVI time series.
04
Emergency Managers
They rely on the AI to quickly assess wildfire damage using burn severity indices.

FAQ

Questions Sentinel Hub owners ask.

01
How do I use this MCP with Claude or Cursor?
Once you subscribe on Vinkius and provide your Sentinel Hub credentials, you simply connect your client to the Vinkius host. Your AI client will then see the available capabilities automatically.
02
What satellite missions can I access?
You can access data from Sentinel-1, Sentinel-2, Sentinel-3, Sentinel-5P, Landsat 8-9, and various Copernicus Land Monitoring services.
03
Do I need to write my own JavaScript for image processing?
No. The MCP includes capabilities to generate ready-to-use evalscripts for common tasks like NDVI, True Color, and False Color imagery.
04
Can I search for images without clouds?
Yes. The search_cloud_free capability allows you to specify a cloud cover threshold to ensure you get clean optical data.
05
Is it possible to perform statistical analysis over time?
Yes. The get_statistics capability supports temporal aggregation, allowing you to calculate mean, min, or max values over daily, weekly, or monthly periods.
06
What is an evalscript and how do I use one?
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 capabilities to get ready-made evalscripts, then pass them to the process_image capability.
07
Can I analyze vegetation health with this server?
Absolutely. Generate an NDVI evalscript with the generate_ndvi_evalscript capability, then process imagery for your area of interest with the process_image capability. For time-series analysis, use the get_statistics capability with temporal aggregation to track vegetation changes over weeks or months. The search_cloud_free capability helps you find clean scenes without cloud contamination.
08
What is the difference between this server and the Copernicus Data Space server?
The Copernicus Data Space server focuses on product catalogue search and download. finding and retrieving raw satellite data files. Sentinel Hub focuses on on-the-fly processing. rendering images, computing indices, and generating statistics without downloading raw data. They complement each other: use Copernicus for data discovery and bulk download, Sentinel Hub for real-time analysis and visualization.

Explore

More in Cloud Infrastructure

Connect Sentinel Hub to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Check sentinel hub status

Generate false color evalscript

Generate ndvi evalscript

Generate true color evalscript

05-08

Get user info

List band combinations

Search by tile

Catalog search

09-11

Get catalog collection

Get catalog item

Get statistics

12-14

List catalog collections

Process image

Search cloud free

What teams actually run

Deforestation Tracking

Wildfire Damage Assessment

Urban Expansion Analysis

Water Resource Monitoring

Building your own app? The connector is yours to use.

Sentinel Hub Connector

Claude Desktop

GIS Professionals

Environmental Scientists

Agricultural Advisors

Emergency Managers

How do I use this MCP with Claude or Cursor?

What satellite missions can I access?

Do I need to write my own JavaScript for image processing?

Can I search for images without clouds?

Is it possible to perform statistical analysis over time?

What is an evalscript and how do I use one?

Can I analyze vegetation health with this server?

What is the difference between this server and the Copernicus Data Space server?

Maxar (Satellite Imagery) AI Connector

Copernicus Data Space AI Connector

INPE (STAC API - Satélites) AI Connector

NASA Earth — Full-Disk Imagery & Natural Events AI Connector

Suggestions

Earth Imagery AI Connector

GOES Satellite Imagery AI Connector

Planet Labs AI Connector

Data Pipeline Prover AI Connector