Sentinel Hub MCP Server for LangChainGive LangChain instant access to 14 tools to Catalog Search, Check Sentinel Hub Status, Generate False Color Evalscript, and more
LangChain is the leading Python framework for composable LLM applications. Connect Sentinel Hub through Vinkius and LangChain agents can call every tool natively. combine them with retrievers, memory, and output parsers for sophisticated AI pipelines.
Ask AI about this App Connector for LangChain
The Sentinel Hub app connector for LangChain is a standout in the Cloud Infrastructure category — giving your AI agent 14 tools to work with, ready to go from day one.
Vinkius delivers Streamable HTTP and SSE to any MCP client
import asyncio
from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with MultiServerMCPClient({
"sentinel-hub": {
"transport": "streamable_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,
)
response = await agent.ainvoke({
"messages": [{
"role": "user",
"content": "Using Sentinel Hub, show me what tools are available.",
}]
})
print(response["messages"][-1].content)
asyncio.run(main())
* 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
About 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.
LangChain's ecosystem of 500+ components combines seamlessly with Sentinel Hub through native MCP adapters. Connect 14 tools via Vinkius and use ReAct agents, Plan-and-Execute strategies, or custom agent architectures. with LangSmith tracing giving full visibility into every tool call, latency, and token cost.
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
The Sentinel Hub MCP Server exposes 14 tools through the Vinkius. Connect it to LangChain in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
All 14 Sentinel Hub tools available for LangChain
When LangChain connects to Sentinel Hub through Vinkius, your AI agent gets direct access to every tool listed below — spanning satellite-imagery, earth-observation, geospatial-data, and more. Every call is secured with network, filesystem, subprocess, and code evaluation entitlements inside a sandboxed runtime. Beyond a simple connection, you get a full AI Gateway with real-time visibility into agent activity, enterprise governance, and optimized token usage.
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
Connect Sentinel Hub to LangChain via MCP
Follow these steps to wire Sentinel Hub into LangChain. The entire setup takes under two minutes — your credentials stay safe behind the Vinkius.
Install dependencies
pip install langchain langchain-mcp-adapters langgraph langchain-openaiReplace the token
[YOUR_TOKEN_HERE] with your Vinkius tokenRun the agent
python agent.pyExplore tools
Why Use LangChain with the Sentinel Hub MCP Server
LangChain provides unique advantages when paired with Sentinel Hub through the Model Context Protocol.
The largest ecosystem of integrations, chains, and agents. combine Sentinel Hub MCP tools with 500+ LangChain components
Agent architecture supports ReAct, Plan-and-Execute, and custom strategies with full MCP tool access at every step
LangSmith tracing gives you complete visibility into tool calls, latencies, and token usage for production debugging
Memory and conversation persistence let agents maintain context across Sentinel Hub queries for multi-turn workflows
Sentinel Hub + LangChain Use Cases
Practical scenarios where LangChain combined with the Sentinel Hub MCP Server delivers measurable value.
RAG with live data: combine Sentinel Hub tool results with vector store retrievals for answers grounded in both real-time and historical data
Autonomous research agents: LangChain agents query Sentinel Hub, synthesize findings, and generate comprehensive research reports
Multi-tool orchestration: chain Sentinel Hub tools with web scrapers, databases, and calculators in a single agent run
Production monitoring: use LangSmith to trace every Sentinel Hub tool call, measure latency, and optimize your agent's performance
Example Prompts for Sentinel Hub in LangChain
Ready-to-use prompts you can give your LangChain agent to start working with Sentinel Hub immediately.
"Show me an NDVI vegetation analysis for the Amazon rainforest region."
"Find cloud-free Sentinel-2 imagery over Paris with less than 10% clouds."
"What band combinations can I use for wildfire assessment?"
Troubleshooting Sentinel Hub MCP Server with LangChain
Common issues when connecting Sentinel Hub to LangChain through the Vinkius, and how to resolve them.
MultiServerMCPClient not found
pip install langchain-mcp-adaptersSentinel Hub + LangChain FAQ
Common questions about integrating Sentinel Hub MCP Server with LangChain.
How does LangChain connect to MCP servers?
langchain-mcp-adapters to create an MCP client. LangChain discovers all tools and wraps them as native LangChain tools compatible with any agent type.