Bring Satellite Imagery
to Pydantic AI
Learn how to connect Copernicus Data Space to Pydantic AI 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 Copernicus Data Space MCP Server?
Connect to the Copernicus Data Space Ecosystem and unlock the world's largest open Earth observation archive directly from your AI agent.
What you can do
- Product Discovery — Search across Sentinel-1 (radar), Sentinel-2 (optical), Sentinel-3 (ocean/land), Sentinel-5P (atmosphere), and Sentinel-6 (altimetry) collections with temporal, spatial, and attribute filters
- Geographic Search — Find satellite products covering any location on Earth using bounding box coordinates or WKT polygon geometries
- Orbit-Based Queries — Retrieve data from specific satellite orbits for interferometry, change detection, and repeat-pass analysis
- Product Inspection — Access complete metadata, quicklook previews, and internal file structure for any product
- Download Orchestration — Generate authenticated download URLs with time-limited Bearer tokens for direct product retrieval
- Data Volume Assessment — Count products matching your criteria before executing full searches
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 in the field below
4. Start querying terabytes of satellite data from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Remote Sensing Analysts — discover and access satellite imagery for land use mapping, urban planning, and environmental monitoring
- Climate Researchers — query long-term data archives for climate change analysis and carbon monitoring
- Agriculture Professionals — find cloud-free imagery for precision farming, crop monitoring, and yield estimation
- Emergency Response Teams — rapidly locate recent satellite acquisitions for disaster assessment and situational awareness
Built-in capabilities (14)
Returns the connection status. Use this to verify your client_id:client_secret credentials are working correctly. Verify Copernicus Data Space API connectivity and authentication
Useful for understanding data volume before executing a full search, or for monitoring data availability trends. Count total products available for a collection and date range
Use collection names like "SENTINEL-2", "SENTINEL-1", or "SENTINEL-3". Get details about a specific Copernicus collection
Returns name, sensing time, footprint geometry, file size, checksum, and all associated attributes. Use this after searching to inspect a specific product before downloading. Get detailed metadata for a specific satellite product by UUID
Returns the direct download URL along with a Bearer token valid for approximately one hour. Use this to download raw satellite data products (typically in SAFE format for Sentinel data). Generate an authenticated download URL for a product
Useful for understanding the product structure and accessing thumbnail previews without downloading the full product. Get quicklook preview and file nodes for a product
This helps you understand what filtering parameters are available (e.g., cloud cover percentage, orbit direction, processing level) for refining product searches. List available metadata attributes for a collection
Includes Sentinel-1 (radar), Sentinel-2 (optical), Sentinel-3 (ocean/land), Sentinel-5P (atmosphere), Sentinel-6 (altimetry), and complementary missions like Landsat. Each entry includes temporal coverage and description. List all available Copernicus satellite data collections
Useful for monitoring new data availability or checking processing pipeline status. List the most recently published satellite products
Returns the hierarchy of files including measurement data, metadata XML, quicklook images, and auxiliary data. Essential for understanding product structure before selective download. List all files contained within a satellite product
Combines spatial filtering with collection and temporal constraints. Ideal for region-specific analysis workflows. Search satellite products within a geographic bounding box
Useful for finding specific orbits, tiles (e.g., "T33UUP" for Sentinel-2 tile), or granule identifiers. Returns product metadata ordered by sensing date. Search satellite products by name pattern
Especially useful for Sentinel-1 (SAR) and Sentinel-2 (optical) repeat-pass analysis, interferometry, and change detection workflows where you need data from the exact same orbit geometry. Search satellite products by orbit number
Specify a collection name (e.g., "SENTINEL-2", "SENTINEL-1"), a date range in YYYY-MM-DD format, and optionally an area of interest as a WKT polygon. Returns product metadata including name, footprint, size, and publication date. Maximum 20 results by default. Search Sentinel satellite products by collection, date range, and area
Why Pydantic AI?
Pydantic AI validates every Copernicus Data Space tool response against typed schemas, catching data inconsistencies at build time. Connect 14 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Copernicus Data Space integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Copernicus Data Space connection logic from agent behavior for testable, maintainable code
Copernicus Data Space in Pydantic AI
Copernicus Data Space and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Copernicus Data Space to Pydantic AI 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 Copernicus Data Space in Pydantic AI
The Copernicus Data Space 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 Pydantic AI 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
Copernicus Data Space for Pydantic AI
Every tool call from Pydantic AI to the Copernicus Data Space MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I get Copernicus OAuth2 credentials?
Register for free at dataspace.copernicus.eu, navigate to your User Settings dashboard, and create a new OAuth client. You'll receive a Client ID and Client Secret — enter them in the format client_id:client_secret. The entire process takes under 2 minutes.
What satellite data is available through this server?
You can access data from all Copernicus Sentinel missions: Sentinel-1 (SAR radar imagery), Sentinel-2 (high-resolution optical imagery at 10m), Sentinel-3 (ocean and land monitoring), Sentinel-5P (atmospheric composition), Sentinel-6 (sea level altimetry), plus complementary data from Landsat, SMOS, and MERIS missions.
Can I download satellite products through this server?
Yes. Use the get_product_download_url tool with a product UUID to generate a time-limited authenticated download URL. The URL and Bearer token are valid for approximately one hour. Products are typically in ESA SAFE format and can range from hundreds of megabytes to several gigabytes.
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your Copernicus Data Space MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai