EOSDA MCP Server for LlamaIndex 12 tools — connect in under 2 minutes
LlamaIndex specializes in data-aware AI agents that connect LLMs to structured and unstructured sources. Add EOSDA as an MCP tool provider through Vinkius and your agents can query, analyze, and act on live data alongside your existing indexes.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
mcp_client = BasicMCPClient("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
mcp_tool_spec = McpToolSpec(client=mcp_client)
tools = await mcp_tool_spec.to_tool_list_async()
agent = FunctionAgent(
tools=tools,
llm=OpenAI(model="gpt-4o"),
system_prompt=(
"You are an assistant with access to EOSDA. "
"You have 12 tools available."
),
)
response = await agent.run(
"What tools are available in EOSDA?"
)
print(response)
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 EOSDA MCP Server
Connect your EOSDA Agriculture API to any AI agent and take full control of satellite-based crop monitoring, vegetation index analysis, weather tracking, and precision agriculture through natural conversation.
LlamaIndex agents combine EOSDA tool responses with indexed documents for comprehensive, grounded answers. Connect 12 tools through Vinkius and query live data alongside vector stores and SQL databases in a single turn. ideal for hybrid search, data enrichment, and analytical workflows.
What you can do
- Field Management — List and register agricultural fields with boundaries, crop types, and planting dates
- Vegetation Indices — Calculate 17+ indices (NDVI, EVI, NDRE, MSAVI, NDMI, etc.) from Sentinel-2 and Landsat
- NDVI Time Series — Track vegetation health trends across entire growing seasons
- EVI Time Series — Monitor enhanced vegetation index for high-biomass and tropical crops
- NDMI Time Series — Monitor crop water content and irrigation needs
- Satellite Imagery — Retrieve raw satellite imagery bands from multiple satellite sources
- Weather Data — Access 20+ years of historical weather data with 1800+ parameters
- Weather Forecast — Get forecasts from 15 days to 7 months for agricultural planning
- Soil Moisture — Monitor soil moisture levels at different depths for irrigation scheduling
- Zoning Maps — Generate productivity and vegetation health zoning maps for precision agriculture
- Index Map Rendering — Create visual vegetation index maps with customizable colormaps
- Custom Field Registration — Add new fields with GeoJSON boundaries for satellite monitoring
The EOSDA MCP Server exposes 12 tools through the Vinkius. Connect it to LlamaIndex in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect EOSDA to LlamaIndex via MCP
Follow these steps to integrate the EOSDA MCP Server with LlamaIndex.
Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save to agent.py and run: python agent.py
Explore tools
The agent discovers 12 tools from EOSDA
Why Use LlamaIndex with the EOSDA MCP Server
LlamaIndex provides unique advantages when paired with EOSDA through the Model Context Protocol.
Data-first architecture: LlamaIndex agents combine EOSDA tool responses with indexed documents for comprehensive, grounded answers
Query pipeline framework lets you chain EOSDA tool calls with transformations, filters, and re-rankers in a typed pipeline
Multi-source reasoning: agents can query EOSDA, a vector store, and a SQL database in a single turn and synthesize results
Observability integrations show exactly what EOSDA tools were called, what data was returned, and how it influenced the final answer
EOSDA + LlamaIndex Use Cases
Practical scenarios where LlamaIndex combined with the EOSDA MCP Server delivers measurable value.
Hybrid search: combine EOSDA real-time data with embedded document indexes for answers that are both current and comprehensive
Data enrichment: query EOSDA to augment indexed data with live information before generating user-facing responses
Knowledge base agents: build agents that maintain and update knowledge bases by periodically querying EOSDA for fresh data
Analytical workflows: chain EOSDA queries with LlamaIndex's data connectors to build multi-source analytical reports
EOSDA MCP Tools for LlamaIndex (12)
These 12 tools become available when you connect EOSDA to LlamaIndex via MCP:
create_field
Accepts field boundary as GeoJSON polygon or coordinates, field name, crop type, and planting date. Returns the created field with ID, calculated area, and monitoring activation status. Essential for onboarding new fields into the monitoring system, expanding farm coverage, and setting up new crop seasons. AI agents should use this when users ask "add a new field for monitoring", "register this field boundary", or need to set up satellite monitoring for a new agricultural area. Register a new agricultural field for satellite monitoring
get_evi_timeseries
EVI is more sensitive in high-biomass regions and less affected by atmospheric conditions than NDVI. Returns EVI values per satellite overpass date for trend analysis. Essential for monitoring dense canopies, tropical crops, and areas with high atmospheric interference. AI agents should reference this when users ask "show me EVI trends for this field", "how is the canopy developing", or need enhanced vegetation index analysis for high-biomass crops. Get EVI time series data for enhanced vegetation monitoring over a growing season
get_fields
Returns field names, boundaries (GeoJSON polygons), area in hectares/acres, crop type, planting dates, and current growth stage information. Essential for farm management overview, field inventory, and selecting target fields for satellite analysis. AI agents should use this when users ask "show me all my fields", "list monitored fields", or need to identify available fields for vegetation index or weather queries. List all agricultural fields monitored in your EOSDA account
get_ndmi_timeseries
NDMI is sensitive to vegetation water content and is used for drought monitoring, irrigation scheduling, and fire risk assessment. Returns NDMI values per satellite overpass date. Essential for water stress detection, irrigation optimization, drought impact assessment, and harvest timing. AI agents should use this when users ask "show me crop water stress trends", "how is the moisture content changing", or need moisture index analysis for irrigation planning. Get NDMI time series data for crop water stress monitoring
get_ndvi_timeseries
Returns NDVI values per satellite overpass date, enabling trend analysis of crop health, growth stages, and stress detection. Essential for season-long crop monitoring, growth curve analysis, yield prediction, and identifying problematic periods. AI agents should use this when users ask "show me the NDVI trend for this season", "how has vegetation health changed over the growing season", or need time-series vegetation analysis. Get NDVI time series data showing vegetation health trends over a growing season
get_satellite_imagery
) for a specific field and date range. Supports Sentinel-2, Landsat 8/9, MODIS, NAIP, and CBERS-4 sources. Returns image metadata, acquisition dates, cloud cover percentages, band availability, and download URLs. Essential for visual crop assessment, custom band analysis, change detection, and downloading raw imagery for further processing. AI agents should reference this when users ask "show me satellite images of my field from last week", "get Sentinel-2 imagery for field X", or need raw satellite imagery download links. Retrieve raw satellite imagery for a specific field and date range
get_soil_moisture
Returns soil moisture levels at different depths (surface, root zone, deep soil), moisture anomalies, and irrigation recommendations. Essential for irrigation scheduling, drought monitoring, water stress detection, and water resource optimization. AI agents should reference this when users ask "what is the soil moisture level in my field", "do I need to irrigate", or need soil moisture data for irrigation planning. Get soil moisture data for agricultural fields
get_vegetation_index
Supports 17+ indices including NDVI (vegetation health), EVI (enhanced vegetation index), GNDVI (green NDVI), NDRE (red edge), MSAVI (soil adjusted), RECI (red edge chlorophyll), NDSI, NDWI (water), SAVI, ARVI, GCI (chlorophyll), SIPI, NBR (burn ratio), MSI (moisture), ISTACK, FIDET, and CCCI. Returns index values, statistics (mean, min, max, std), satellite source (Sentinel-2, Landsat), and cloud cover percentage. Essential for crop health assessment, stress detection, and growth monitoring. AI agents should use this when users ask "what is the NDVI for my corn field this month", "calculate vegetation health for field X", or need vegetation index analysis. Calculate vegetation indices (NDVI, EVI, NDRE, etc.) for a specific field and date range
get_weather_data
Includes 1800+ weather parameters: temperature (air, soil), precipitation, humidity, wind speed/direction, solar radiation, evapotranspiration, dew point, pressure, and growing degree days. Historical data available since 1979. Essential for irrigation planning, frost risk assessment, disease/pest pressure modeling, and yield prediction. AI agents should use this when users ask "what was the weather like on my field last month", "get temperature and rainfall data", or need historical weather analysis for crop management decisions. Get historical and current weather data for agricultural fields
get_weather_forecast
Includes temperature, precipitation, humidity, wind, and solar radiation forecasts. Essential for planting schedule optimization, harvest timing, irrigation planning, frost protection, and seasonal crop management. AI agents should reference this when users ask "what is the weather forecast for my field next week", "get seasonal precipitation forecast", or need forward-looking weather data for agricultural planning. Get weather forecasts (15 days to 7 months) for agricultural fields
get_zoning_map
Returns zone boundaries, average index values per zone, area percentages, and management recommendations. Essential for variable rate application (VRA), precision fertilization, targeted irrigation, and yield optimization. AI agents should use this when users ask "create a zoning map for my field", "generate productivity zones", or need management zone maps for precision agriculture. Generate productivity and vegetation health zoning maps for fields
render_index_map
Returns rendered raster images (JPEG, PNG, or GeoTIFF) with color-coded vegetation index values overlaid on field boundaries. Supports colormaps like NDVI (green-yellow-red), thermal, grayscale, and custom color schemes. Essential for field reports, stakeholder communication, visual crop assessment, and creating shareable vegetation maps. AI agents should reference this when users ask "create a color-coded NDVI map of my field", "generate a vegetation health visualization", or need shareable vegetation index images for reports. Generate visual vegetation index maps with customizable colormaps for field visualization
Example Prompts for EOSDA in LlamaIndex
Ready-to-use prompts you can give your LlamaIndex agent to start working with EOSDA immediately.
"Show me the NDVI trend for my corn field over the 2025 growing season."
"What is the 15-day weather forecast and current soil moisture for my soybean field?"
"Generate a productivity zoning map for my wheat field with 4 zones."
Troubleshooting EOSDA MCP Server with LlamaIndex
Common issues when connecting EOSDA to LlamaIndex through the Vinkius, and how to resolve them.
BasicMCPClient not found
pip install llama-index-tools-mcpEOSDA + LlamaIndex FAQ
Common questions about integrating EOSDA MCP Server with LlamaIndex.
How does LlamaIndex connect to MCP servers?
Can I combine MCP tools with vector stores?
Does LlamaIndex support async MCP calls?
Connect EOSDA with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect EOSDA to LlamaIndex
Get your token, paste the configuration, and start using 12 tools in under 2 minutes. No API key management needed.