How to Use the EOSDA MCP in LlamaIndex

Q: How do I add the EOSDA tools to my LlamaIndex application?

You use the McpToolSpec and point it at your Vinkius server endpoint. This automatically generates LlamaIndex tools for every operation on the MCP server, like getsatelliteimagery and getzoningmap, ready to be added to your agent.

Q: Can a LlamaIndex agent use EOSDA to create and then monitor a new field?

Absolutely. Your agent can first call the createfield tool with a new GeoJSON boundary. LlamaIndex can then index the new field ID, making it immediately available for follow-up queries using tools like getndvitimeseries.

Q: How does LlamaIndex handle data from EOSDA for RAG?

LlamaIndex's McpToolSpec converts the output from EOSDA tools into documents that can be placed into a vector index. This means historical weather from getweatherdata or a season's worth of getevitimeseries readings become searchable context for your agent.

Ground your LlamaIndex agents in real-world agricultural data from EOSDA.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect EOSDA MCP to LlamaIndex

Create your Vinkius account to connect EOSDA to LlamaIndex 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 with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Field Data as Knowledge

Turn raw API calls into a searchable knowledge base. When your LlamaIndex agent calls `get_fields`, the returned list of field names, boundaries, and crop types is indexed into your vector store. The next time you ask, "what's the area of my main corn field?" the agent answers from its memory, without needing another API call. This creates a persistent, queryable state for your farm. Run `get_weather_data` for the past season and index it. Now your agent has a historical context it can retrieve with semantic search, letting you ask complex questions about past conditions.

Build a RAG System with LlamaIndex

Combine static documents with live field data for a complete picture. Your agent can answer a question by pulling from a research paper on crop disease and then checking live `get_ndmi_timeseries` data from this MCP server to see if your fields show signs of water stress, a key factor. This is the core of a good RAG system: augmenting retrieved knowledge with fresh, real-world data. Your agent doesn't just know what the book says; it knows what's happening in your field right now by using tools like `get_soil_moisture` and `get_vegetation_index`.

Query Your Farm's History

Because LlamaIndex makes tool outputs part of a queryable log, you can analyze operations over time. After a few weeks of monitoring, you can ask your agent, "Show me all fields where NDVI dropped during that heatwave in July," and it can correlate indexed `get_ndvi_timeseries` data with indexed `get_weather_data`. This turns your agent into an analytical partner. It's not just for one-off tasks like using `render_index_map`. It's for building a deep understanding of your farm's performance over an entire season, with all the data stored and indexed for easy retrieval.

Setup guide

Set up EOSDA MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all EOSDA MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to EOSDA tools.",
)
response = await agent.run("List recent EOSDA data")

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 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 MCP in LlamaIndex

You use the `McpToolSpec` and point it at your Vinkius server endpoint. This automatically generates LlamaIndex tools for every operation on the MCP server, like `get_satellite_imagery` and `get_zoning_map`, ready to be added to your agent.

Absolutely. Your agent can first call the `create_field` tool with a new GeoJSON boundary. LlamaIndex can then index the new field ID, making it immediately available for follow-up queries using tools like `get_ndvi_timeseries`.

LlamaIndex's `McpToolSpec` converts the output from EOSDA tools into documents that can be placed into a vector index. This means historical weather from `get_weather_data` or a season's worth of `get_evi_timeseries` readings become searchable context for your agent.

The MCP server provides a standardized, secure, and managed interface. You don't have to write custom loaders or parsers for the EOSDA API; the `McpToolSpec` does that for you. It's a faster, more secure way to get high-quality data into your LlamaIndex knowledge base.

The Vinkius-hosted MCP server is stateless. However, when you use LlamaIndex, the outputs from tools like `get_fields` or `get_soil_moisture` are often stored in your vector database. The security of your farm's operational data then becomes about securing that database, which is under your control.

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