How to Use the Agro MCP in Vercel AI SDK

Q: How do I get historical weather for a farm with the Agro server and Vercel AI SDK?

Your agent just needs to call the gethistoricalweather tool with a polygon ID and a date range. The Vercel AI SDK will stream the results directly into your UI components. You can build a chart that populates as the data arrives.

Q: Can I search for satellite images of a specific field?

Yes. Once you've defined an area with createpolygon, you can use the searchimagery tool. It takes a polygon ID and date range to find relevant satellite photos for analysis.

Q: What's the best way to manage field boundaries with the Agro MCP and Vercel AI SDK?

Use the polygon tools. createpolygon makes a new one, updatepolygon changes it, and listpolygons shows all of them. Since the Vercel AI SDK is for UIs, you can build a map interface that calls these tools in the background.

Q: Does the Agro server work with the Vercel AI SDK for NDVI data?

Absolutely. Call getndvihistory with a polygon ID. The tool returns both NDVI and EVI data, which you can stream right into a chart or a map overlay in your Next.js or React application.

Stream live farm data into your Next.js app with the Vercel AI SDK. Your users see weather and soil stats appear in real-time, no spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Agro MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Live Dashboards for Any Field

Build a front-end that shows real-time farm conditions. Your agent can call `get_current_weather` and `get_current_soil`, and the data streams directly into your React components. No waiting for the whole request to finish. The Vercel AI SDK lets you build UIs where numbers and charts update as the data arrives. You can show a user the UV index from `get_current_uvi` instantly, then populate historical charts with `get_historical_weather` as it loads in the background. It feels fast because it is.

Map and Analyze Plots on the Fly

Let users draw and manage their fields directly in your app. Your agent uses `create_polygon` to save a new field boundary. Then, it can immediately fetch NDVI history with `get_ndvi_history` for that specific area. Because tool results stream, the user experience is interactive. They define a polygon, and your UI can start showing satellite imagery from `search_imagery` for that zone before the full data payload even finishes. It's a responsive way to work with geographic data.

Show What's Coming with this MCP Server

This isn't just about current conditions. Use the Vercel AI SDK to build forecast UIs that populate live. Your agent can call `get_forecast_weather` and `get_forecast_uvi` to give farmers a heads-up. The data streams straight from the Agro MCP server to your user's browser. That means you can build components that show predicted rainfall from `get_accumulated_precipitation` or temperature changes from `get_accumulated_temperature` as they're calculated.

Setup guide

Set up Agro 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 Agro 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 Agro 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 AgroMonitoring. 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 Agro 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 Agro MCP in Vercel AI SDK

Your agent just needs to call the `get_historical_weather` tool with a polygon ID and a date range. The Vercel AI SDK will stream the results directly into your UI components. You can build a chart that populates as the data arrives.

Yes. Once you've defined an area with `create_polygon`, you can use the `search_imagery` tool. It takes a polygon ID and date range to find relevant satellite photos for analysis.

Use the polygon tools. `create_polygon` makes a new one, `update_polygon` changes it, and `list_polygons` shows all of them. Since the Vercel AI SDK is for UIs, you can build a map interface that calls these tools in the background.

Absolutely. Call `get_ndvi_history` with a polygon ID. The tool returns both NDVI and EVI data, which you can stream right into a chart or a map overlay in your Next.js or React application.

The server only handles agricultural and geospatial data you provide, like polygon coordinates and date ranges for queries. It doesn't see your user data. Vinkius secures the connection with a unique token, and all processing happens in an ephemeral sandbox that's destroyed after your request.

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