How to Use the EOSDA MCP in Claude Code

Q: How do I add the EOSDA MCP Server to Claude Code?

Run claude mcp add --transport http eosda-mcp -- . Ensure you put the transport flag before the server name. Verify the connection by typing claude mcp list.

Q: Can Claude Code and EOSDA generate variable rate zoning maps?

Yes. The CLI calls getzoningmap to retrieve productivity boundaries and area percentages. It pipes those management recommendations directly into your tractor's application software.

Q: Does the EOSDA integration in Claude Code track historical weather?

getweatherdata provides over 1800 parameters dating back to 1979. You can write shell scripts that ask the agent to extract specific growing degree days and dump them into your data warehouse.

Q: How do I pull raw satellite imagery via the terminal?

Tell the agent to run getsatelliteimagery for a specific date range. It returns the cloud cover percentages and download URLs, which you can easily pass to wget or curl.

Connect Claude Code to the EOSDA MCP Server to run headless agricultural data pipelines and trigger irrigation scripts from your terminal.

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 Claude Code

Create your Vinkius account to connect EOSDA to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless Crop Monitoring with Claude Code

`get_soil_moisture` returns surface and root zone saturation metrics directly to your standard output. The MCP connection lets Claude Code run this in the background as part of a scheduled CI/CD pipeline. You pipe the JSON response into your irrigation controller without touching a browser. When moisture drops below a threshold, the CLI queries `get_weather_forecast` to check for incoming rain. If the 15-day forecast shows dry conditions, the agent executes your custom bash scripts to open the water valves.

Terminal-Driven Field Registration

`create_field` takes a GeoJSON boundary and registers it for active satellite monitoring. You feed Claude Code a directory of shapefiles, and it processes them headlessly. The agent maps the coordinates and returns the assigned field IDs to your terminal. To verify the setup, run a quick command to trigger `get_fields`. The CLI lists the crop types, planting dates, and calculated areas. You get instant confirmation that your new monitoring zones are active.

Automated Vegetation Analysis

`get_evi_timeseries` extracts enhanced vegetation index values for high-biomass regions. Claude Code pulls this data over an SSH session to evaluate canopy development. It formats the raw satellite overpass metrics into a clean CSV for your agronomy team. For visual reporting, the agent triggers `render_index_map`. It downloads the color-coded raster images straight to your server. You build automated cron jobs that email these GeoTIFFs to stakeholders every Monday morning.

Setup guide

Set up EOSDA MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see eosda-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest EOSDA transactions." It will automatically discover and invoke the available EOSDA tools.

Terminal

claude mcp add --transport http eosda-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the EOSDA MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "eosda-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Code

Run `claude mcp add --transport http eosda-mcp -- `. Ensure you put the transport flag before the server name. Verify the connection by typing `claude mcp list`.

Yes. The CLI calls `get_zoning_map` to retrieve productivity boundaries and area percentages. It pipes those management recommendations directly into your tractor's application software.

`get_weather_data` provides over 1800 parameters dating back to 1979. You can write shell scripts that ask the agent to extract specific growing degree days and dump them into your data warehouse.

Tell the agent to run `get_satellite_imagery` for a specific date range. It returns the cloud cover percentages and download URLs, which you can easily pass to `wget` or `curl`.

The integration handles precise geographic coordinates and historical yield metrics. Vinkius enforces a strict ephemeral architecture, ensuring your terminal commands and location data vanish the second the MCP connection closes.

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