How to Use the Ambee Soil MCP in Vercel AI SDK

Q: How do I use Ambee Soil with the Vercel AI SDK to build a soil map?

You'll use the getgridsoil tool. Hook it up to the streamText function from the Vercel AI SDK and feed the streaming results directly into your map component. Your map will update in real-time as the grid data arrives.

Q: Can I stream historical Ambee Soil data into a React chart using the Vercel AI SDK?

Yes, that's exactly what it's for. Call the gethistoricalsoil tool and stream the output. Your charting library can then render the data points as they come in, drawing the trend line live for the user.

Q: What's the best way to get live soil properties from Ambee Soil in a Next.js app with the Vercel AI SDK?

Call the getlatestsoil and getsoilproperties tools. When you stream the results into your React components, the UI will populate with the data piece by piece, creating a fast, non-blocking user experience.

Stream real-time Ambee Soil data directly into your UI with the Vercel AI SDK. No spinners, just data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ambee Soil MCP to Vercel AI SDK

Create your Vinkius account to connect Ambee Soil 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 Ambee Soil with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Live Soil Condition Maps

Stop making your users wait for a full map to load. With the Vercel AI SDK, you can use the `get_grid_soil` tool to stream spatial data directly into your Next.js or React components. Your users will see the soil moisture and temperature map build itself right before their eyes, cell by cell. This isn't a batch request that blocks the UI. The data flows in as it's processed, making your ag-tech app feel incredibly responsive. You're not just showing data; you're showing the data as it arrives, which is a completely different experience.

Stream Data into Charts with the Vercel AI SDK

When a user wants to see a 30-day soil moisture trend, don't show them a loading skeleton. Use the `get_historical_soil` tool and stream the results. Your chart component will populate point-by-point, drawing the trend line live as the data comes in from the Ambee Soil MCP server. This approach gives your dashboards an immediate, interactive feel. You can build frontends that let farmers and analysts explore soil condition trends without the typical lag of a request-response cycle. It just works.

Get Instant Spot-Checks on a Map

Combine `get_latest_soil` and `get_soil_properties` for instant feedback. A user clicks a point on a map in your app, and a sidebar immediately starts filling with the current soil moisture, temperature, pH, and organic carbon content. The data appears as it's fetched, not all at once after a delay. Because the Vercel AI SDK streams tool outputs, your UI never freezes. It’s the right way to build user-facing tools for precision agriculture. The information feels immediate because it is.

Setup guide

Set up Ambee Soil 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 Ambee Soil 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 Ambee Soil 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 Ambee. 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 Ambee Soil 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 Ambee Soil MCP in Vercel AI SDK

You'll use the `get_grid_soil` tool. Hook it up to the `streamText` function from the Vercel AI SDK and feed the streaming results directly into your map component. Your map will update in real-time as the grid data arrives.

Yes, that's exactly what it's for. Call the `get_historical_soil` tool and stream the output. Your charting library can then render the data points as they come in, drawing the trend line live for the user.

Call the `get_latest_soil` and `get_soil_properties` tools. When you stream the results into your React components, the UI will populate with the data piece by piece, creating a fast, non-blocking user experience.

Yes. The connection to the MCP Server is a standard HTTP request, so it works perfectly from any Edge Function. You can fetch and stream soil data with low latency, close to your users.

Your location coordinates and the resulting soil data are only used for the transaction. Vinkius runs each MCP server in an ephemeral sandbox, meaning the instance handling your request is destroyed after it's done. Your data isn't stored or logged.

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