How to Use the EOSDA Agriculture Satellite Data MCP in LangChain

Q: How can I find all available imagery for a specific field with EOSDA Agriculture Satellite Data and LangChain?

Your agent can call the searchmultidataset tool. Just provide it with the field's boundary as a GeoJSON polygon and a date range. It will return a list of all scenes from every supported dataset, like Sentinel and Landsat, that match your query.

Q: Can I automate NDVI analysis for my farm using EOSDA Agriculture Satellite Data in a LangChain agent?

Yes. You'll build a chain where the agent first calls searchdataset to find a suitable recent image, then passes that scene ID to createvegetationtask. The final step in the chain is to use gettaskresult with the task ID to fetch the download link for the NDVI map.

Q: What's the difference between searchdataset and searchmultidataset?

Use searchdataset when you want imagery from a single, specific satellite source, like 'Sentinel-2'. Use searchmultidataset when you want to see everything available for your area of interest across all supported satellite platforms in one call.

Q: How do I know which vegetation indices I can request?

Before you ask for an analysis, have your agent call getavailableindices. This tool returns a simple list of all the valid index names (like NDVI, EVI, NDRE) that you can use as a parameter when you call createvegetationtask.

Build automated agricultural analysis chains for your LangChain agents to monitor crop health and find the best satellite imagery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect EOSDA Agriculture Satellite Data MCP to LangChain

Create your Vinkius account to connect EOSDA Agriculture Satellite Data 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 EOSDA Agriculture Satellite Data with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Image Search to Analysis

This isn't about running one-off tasks. It's about building an automated sequence. Your LangChain agent can first run `search_dataset` to find the most recent satellite image with the lowest cloud cover for your field. Once it has the best scene ID, the next link in the chain automatically calls `create_vegetation_task` to kick off an NDVI analysis. The agent then polls `get_task_result` until the processing is done, finally returning a direct download link to the GeoTIFF file. You build it once, and it runs on its own.

Make Decisions Based on Data

Give your agents the tools to make smarter choices. Before running a costly analysis, an agent can check `get_available_indices` to confirm the right vegetation index is supported for its goal. It can use `get_available_datasets` to see if a higher-resolution sensor is an option. This lets you build sophisticated logic chains. For example: an agent can be tasked to monitor a field, but it will only trigger a new `create_vegetation_task` if `search_dataset` finds an image with less than 10% cloud cover from the last 48 hours. It's about controlling your process and your costs.

Build Custom Ag-Data Pipelines

Connect satellite data to the rest of your operation. Since LangChain is all about integrations, the output from `get_task_result` — like a soil moisture data file — doesn't have to be the end of the line. It can be the input for another tool entirely. Send that data to a custom tool that updates your irrigation system, logs the field's health in a database, or sends an alert to a Slack channel. This MCP Server gives your agents the raw agricultural intelligence; LangChain lets you build the full, end-to-end workflow around it.

Setup guide

Set up EOSDA Agriculture Satellite Data 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 EOSDA Agriculture Satellite Data 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({
    "eosda-agriculture-satellite-data-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 EOSDA Agriculture Satellite Data 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 EOSDA. 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 EOSDA Agriculture Satellite Data 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 EOSDA Agriculture Satellite Data MCP in LangChain

Your agent can call the `search_multi_dataset` tool. Just provide it with the field's boundary as a GeoJSON polygon and a date range. It will return a list of all scenes from every supported dataset, like Sentinel and Landsat, that match your query.

Yes. You'll build a chain where the agent first calls `search_dataset` to find a suitable recent image, then passes that scene ID to `create_vegetation_task`. The final step in the chain is to use `get_task_result` with the task ID to fetch the download link for the NDVI map.

Use `search_dataset` when you want imagery from a single, specific satellite source, like 'Sentinel-2'. Use `search_multi_dataset` when you want to see everything available for your area of interest across all supported satellite platforms in one call.

Before you ask for an analysis, have your agent call `get_available_indices`. This tool returns a simple list of all the valid index names (like NDVI, EVI, NDRE) that you can use as a parameter when you call `create_vegetation_task`.

The server only processes the data you provide for each call, like the GeoJSON polygon defining your field and the requested date range. LangChain passes this data to the MCP Server endpoint. The server itself is ephemeral; it doesn't store your query history. Your primary security focus should be protecting your Vinkius endpoint token within your LangChain environment.

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