How to Use the Wiagro MCP in Vercel AI SDK

Q: What if I need to check the structural integrity of my storage units with Vercel AI SDK?

You use getrupturealerts for that. This tool returns details about any tears or holes found on silobags, including severity and location. It’s a quick way to assess physical risk across your facility.

Q: Can I monitor the overall health of my sensor network using Wiagro and Vercel AI SDK?

Yep. Call getsensorhealth for a full status check. This gives you IDs, battery levels, signal strength, and last communication times for every deployed sensor. It's key for system administration.

Q: Does Wiagro support checking multiple storage units simultaneously with Vercel AI SDK?

Absolutely. By calling getsilobags first, you get a list of all available IDs. Then, you can pass those IDs to other tools like getqualityassessment to check status across the entire facility.

Real-time grain monitoring results streamed directly into your React frontends with 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 Wiagro MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Alerts and Condition Checks via MCP Server

The `get_alerts` tool handles proactive grain management. It returns alert severity, affected silobags, and recommended actions immediately when a user asks for active alerts. When you call the MCP Server with this data, your AI client streams the resulting critical or warning information right into the UI. Users see exactly what needs attention without waiting for a full page refresh.

Facility Overview and Inventory Status

You can pull facility-wide status using `get_facility_overview`. This gives management an immediate summary of all monitored silobags. It's perfect for executive dashboards where a quick, high-level quality assessment matters. The `get_silobags` tool helps too; it lists every unit and its current monitoring status. Your AI client streams this inventory list, letting the end user see which storage units are in play before they even check sensor data.

Historical Trend Analysis with Vercel AI SDK

Spoilage tracking requires looking backward. The `get_co2_history` tool fetches time-series CO2 data, which is critical for spotting trends. Your agent can query this historical data and display the ppm readings streaming live to the user. Need moisture migration analysis? Use `get_humidity_history`. This delivers historical humidity percentages over time, letting your client visualize stability issues as they appear in real-time on the screen.

Setup guide

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

The MCP Server streams data results directly into your frontend. When an agent calls a tool like `get_current_readings`, the user sees the sensor values (temperature, CO2, humidity) appear instantly, not after a loading spinner.

You use `get_rupture_alerts` for that. This tool returns details about any tears or holes found on silobags, including severity and location. It’s a quick way to assess physical risk across your facility.

Yep. Call `get_sensor_health` for a full status check. This gives you IDs, battery levels, signal strength, and last communication times for every deployed sensor. It's key for system administration.

Absolutely. By calling `get_silobags` first, you get a list of all available IDs. Then, you can pass those IDs to other tools like `get_quality_assessment` to check status across the entire facility.

This server touches sensor readings (temperature, CO2, humidity), quality scores, and silobag metadata. All operational monitoring is managed through a single endpoint token for secure access.

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