How to Use the Copernicus Data Space MCP in LangChain

Q: Can I trace Copernicus Data Space tool calls using LangChain with LangSmith?

Yes, every single call to tools like searchbybbox or getproductdownloadurl is fully traced. You can inspect the exact coordinates, Sentinel collection names, and execution times directly in your LangSmith dashboard.

Q: What happens if a Sentinel search returns too many files?

Your agent can use countproducts to check the volume before pulling metadata. If the count is high, you can instruct your model to narrow the bounding box or dates.

Get raw satellite data straight into your LangChain chains and trace every step with LangSmith.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Copernicus Data Space MCP to LangChain

Create your Vinkius account to connect Copernicus Data Space to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Copernicus Data Space with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Step Satellite Search Pipeline

Let your LangChain agent decide when to run `search_products` based on geographic regions and then immediately call `get_product_download_url` to grab the actual data. You configure the chain, and the model handles the sequence, looking up collections via `list_collections` first if it needs to verify the exact Sentinel platform name. Because LangChain supports complex ReAct loops, your agent can inspect the footprint geometry from one run and feed it into `search_by_bbox` for adjacent tiles. You see every tool transition inside LangSmith, meaning you can easily debug why a specific Sentinel-2 tile was chosen over another.

Smart Filter Validation with MCP Server

Stop guessing which metadata filters work for Sentinel-1 versus Sentinel-3. Your LangChain agent can query `list_attributes` to pull valid parameters on the fly, dynamically constructing precise queries before running `search_products`. This MCP Server setup prevents broken chains by letting the agent self-correct when a search fails. If a query returns zero results, the model checks `count_products` to see if shifting the date range or cloud cover limits will yield valid Sentinel files.

On-Demand Preview Generation

Pull quicklook thumbnails directly into your LangChain agentic workflow to verify image quality before committing to a massive download. The model runs `get_quicklook` to fetch the preview, letting you build custom logic that filters out cloud-heavy imagery. After validating the preview, the agent triggers `list_product_nodes` to map out the internal file structure of the SAFE format. This keeps your pipeline lightweight because you only request a token for the specific assets you actually need via `get_product_download_url`.

Setup guide

Set up Copernicus Data Space MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Copernicus Data Space tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "copernicus-data-space-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Copernicus Data Space transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Copernicus Data Space. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Copernicus Data Space now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Copernicus Data Space MCP in LangChain

You initialize the MCP Server adapter in python, register the 14 satellite tools, and pass them directly to your LangChain agent. This lets your agent run spatial queries and fetch download tokens natively during a conversation.

Yes, every single call to tools like `search_by_bbox` or `get_product_download_url` is fully traced. You can inspect the exact coordinates, Sentinel collection names, and execution times directly in your LangSmith dashboard.

Vinkius manages your Copernicus API credentials securely, exposing a single endpoint. Your LangChain code simply uses your Vinkius token, and the server handles generating the temporary Bearer tokens when calling `get_product_download_url`.

Your agent can use `count_products` to check the volume before pulling metadata. If the count is high, you can instruct your model to narrow the bounding box or dates.

We run this MCP Server in an isolated, zero-trust sandbox that never stores your spatial queries, bounding boxes, or Sentinel download tokens. All API requests to the Copernicus catalog are ephemeral and wiped the moment your LangChain run finishes.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript