How to Use the AgroLog MCP in Vercel AI SDK

Q: Can my Vercel AI SDK agent turn on grain silo fans via AgroLog?

Yes, the agent calls setrelaystate with the specific device ID and relay name. You should implement a confirmation step in your UI before allowing the agent to change physical relay states to true or false.

Q: How does the agent know which silos belong to which farm?

The getcustomerdevices tool returns a scoped list of device IDs and names for a specific organization. Your agent uses this list to filter queries so users only see their own temperature and crop level readings.

Q: Will the Vercel AI SDK stream AgroLog weather data as it arrives?

The agent fetches the latest ten readings via getweather and streams that text response block by block to the frontend. It feels instantaneous to the user asking about current wind speed or rainfall.

Build live grain monitoring dashboards by connecting the AgroLog MCP Server to your Vercel AI SDK frontend.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AgroLog MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Sensor Data to React

`get_device_telemetry` pulls historical data points for temperature, moisture, and CO2 directly into your Vercel AI SDK application. The user sees their grain silo conditions populate in real-time as the text streams to the client. Using `get_devices`, your agent identifies the correct sensors and formats the response for your UI components. You don't make users wait for a loading spinner while querying 48 hours of moisture trends.

AgroLog MCP Server Alerting

`get_alarms` fetches critical threshold breaches for high temperature or elevated CO2 across your grain storage facilities. Your agent queries this endpoint and immediately streams the warning severity and affected device ID to the user's dashboard. Early detection matters for grain quality. When a user asks about active alerts, the model checks the alarm status and renders the exact equipment failure or moisture spike requiring attention.

Trigger Aeration from the UI

`set_relay_state` flips physical relays on or off for fans, aeration systems, and dryers connected to the AgroLog device. Your Next.js app can render a button that tells the agent to activate ventilation when moisture hits critical levels. Before flipping a switch, the agent can call `get_weather` to confirm outdoor air conditions suit natural air drying. The user gets a fluid, conversational interface for managing heavy agricultural equipment.

Setup guide

Set up AgroLog 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 AgroLog 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 AgroLog 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 AgroLog. 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 AgroLog 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 AgroLog MCP in Vercel AI SDK

Install @ai-sdk/mcp and instantiate createMCPClient with your HTTP transport URL. Pass the resulting mcpClient.tools() into your streamText call to give your agent access to silo data.

Yes, the agent calls set_relay_state with the specific device ID and relay name. You should implement a confirmation step in your UI before allowing the agent to change physical relay states to true or false.

The get_customer_devices tool returns a scoped list of device IDs and names for a specific organization. Your agent uses this list to filter queries so users only see their own temperature and crop level readings.

The agent fetches the latest ten readings via get_weather and streams that text response block by block to the frontend. It feels instantaneous to the user asking about current wind speed or rainfall.

The integration operates in a V8 Isolate Sandbox where your headspace gas readings and temperature telemetry remain isolated. The connection requires a single endpoint token, ensuring your historical crop data never leaks across sessions or persists in the transport layer.

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