How to Use the Farmonaut MCP in Vercel AI SDK

Q: How do I stream Farmonaut vegetation indices using Vercel AI SDK and MCP?

Call getndvi or getevi inside your streamText function. The Vercel AI SDK handles the tool execution payload, allowing your UI to render the satellite source and cloud cover percentages as they stream from the server.

Q: Can I map field boundaries with Farmonaut and Vercel AI SDK?

Yes. Use the addfield tool to send GeoJSON boundaries from your frontend map component. The Vercel AI SDK streams the resulting field ID and calculated acreage back to your application state instantly.

Q: How does Vercel AI SDK handle the Farmonaut MCP Server weather forecasts on the edge?

The SDK executes getweatherforecast within Edge Functions. It bypasses cold starts to fetch temperature, solar radiation, and precipitation predictions, rendering the data in your React components under 100ms.

Q: What is the best way to switch between NDVI and EVI data using this MCP Server?

Let your agent choose. It will call getevi for dense, high-biomass canopies where NDVI saturates, or getndvi for standard crop health checks, feeding the raw index statistics directly into your stream.

Render live satellite crop data directly in your Next.js frontend with the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Farmonaut MCP to Vercel AI SDK

Create your Vinkius account to connect Farmonaut to Vercel AI SDK 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 Farmonaut with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Visualizing Field Health Instantly

The `get_ndvi` tool pulls raw vegetation health indexes directly into your Vercel AI SDK stream. Instead of making users wait for a full page reload, your app streams the crop vigor statistics and satellite source data directly into React components as the model processes the numbers. You can pair this with `get_satellite_images` to render true-color and false-color overlays side-by-side. The model reads the raw spectral bands, outputs the URL, and your frontend paints the field map without a single loading spinner.

Live Weather Feeds for React UIs

The `get_weather` tool fetches air temperature, precipitation, and evapotranspiration data for any registered field coordinates. Using the Vercel AI SDK, your chat interface displays historical weather tables instantly while the model explains the agronomic impact. When users plan their week, the model calls `get_weather_forecast` to stream upcoming wind and humidity trends. It binds the weather metrics straight to your custom UI widgets on the edge, keeping latency under 100 milliseconds.

Building Interactive Farm Dashboards with MCP

The `add_field` tool registers new GeoJSON boundaries and crop types directly from a user's map selection. This Farmonaut MCP Server integration lets your AI client validate field polygons and activate satellite monitoring in real-time. Once registered, the model uses `get_fields` to populate the user's dashboard sidebar dynamically. The Vercel AI SDK handles the state updates on the fly, rendering active acreages and planting dates without manual API glue code.

Setup guide

Set up Farmonaut MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Farmonaut tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Farmonaut transactions",
});

console.log(text);
await mcpClient.close();

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 Farmonaut. 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 Farmonaut 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 Farmonaut MCP in Vercel AI SDK

Call `get_ndvi` or `get_evi` inside your `streamText` function. The Vercel AI SDK handles the tool execution payload, allowing your UI to render the satellite source and cloud cover percentages as they stream from the server.

Yes. Use the `add_field` tool to send GeoJSON boundaries from your frontend map component. The Vercel AI SDK streams the resulting field ID and calculated acreage back to your application state instantly.

The SDK executes `get_weather_forecast` within Edge Functions. It bypasses cold starts to fetch temperature, solar radiation, and precipitation predictions, rendering the data in your React components under 100ms.

Let your agent choose. It will call `get_evi` for dense, high-biomass canopies where NDVI saturates, or `get_ndvi` for standard crop health checks, feeding the raw index statistics directly into your stream.

Your GeoJSON boundaries and field coordinates are processed inside Vinkius's zero-trust V8 sandbox. The server never persists your spatial data; it only passes coordinates to the satellite API via encrypted HTTP requests, keeping your farm boundaries private.

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