Bring Satellite Imagery
to CrewAI
Learn how to connect Sentinel Hub to CrewAI and start using 14 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Sentinel Hub MCP Server?
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
Built-in capabilities (14)
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
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
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
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
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 detailed information about a specific data collection
Use the item ID returned from a catalog_search query. Get detailed metadata for a specific STAC catalog item
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
Useful for verifying credentials and understanding available quotas. Get authenticated Sentinel Hub user profile information
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
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
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
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
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
Why CrewAI?
When paired with CrewAI, Sentinel Hub becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Sentinel Hub tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.
- —
Multi-agent collaboration lets you decompose complex workflows into specialized roles, one agent researches, another analyzes, a third generates reports, each with access to MCP tools
- —
CrewAI's native MCP integration requires zero adapter code: pass Vinkius Edge URL directly in the
mcpsparameter and agents auto-discover every available tool at runtime - —
Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls
- —
Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports
Sentinel Hub in CrewAI
Sentinel Hub and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Sentinel Hub to CrewAI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Sentinel Hub in CrewAI
The Sentinel Hub MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 14 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in CrewAI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Sentinel Hub for CrewAI
Every tool call from CrewAI to the Sentinel Hub MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
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 tools to get ready-made evalscripts, then pass them to the process_image tool.
Can I analyze vegetation health with this server?
Absolutely. Generate an NDVI evalscript with the generate_ndvi_evalscript tool, then process imagery for your area of interest with the process_image tool. For time-series analysis, use the get_statistics tool with temporal aggregation to track vegetation changes over weeks or months. The search_cloud_free tool 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.
How does CrewAI discover and connect to MCP tools?
CrewAI connects to MCP servers lazily. when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.
Can different agents in the same crew use different MCP servers?
Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.
What happens when an MCP tool call fails during a crew run?
CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.
Can CrewAI agents call multiple MCP tools in parallel?
CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.
Can I run CrewAI crews on a schedule (cron)?
Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.
MCP tools not discovered
Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts. check console output.
Agent not using tools
Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".
Timeout errors
CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.
Rate limiting or 429 errors
Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.