How to Use the EOSDA MCP in Vercel AI SDK

Q: Can I stream satellite imagery directly to the UI?

Yes. Tools like renderindexmap return raster image data. The SDK streams this response so your React components can render the visual crop assessment as it arrives.

Stream live EOSDA satellite crop data directly into your React frontends using 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 EOSDA MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vercel AI SDK live vegetation tracking

`get_ndvi_timeseries` and `get_evi_timeseries` stream raw vegetation health metrics straight to your user's browser. Pass the field ID to the MCP Server. The AI client streams historical overpass values directly into your Next.js charts before the backend finishes processing the full request. High-biomass regions require specific data for accurate canopy assessment. Your application hits `get_vegetation_index` to pull statistics across 17 index types. Users watch the agricultural data populate live on their dashboards.

Render agricultural maps on the edge

`render_index_map` generates color-coded raster images of your field boundaries. The SDK streams the resulting JPEG or GeoTIFF data directly to the client UI. You don't make users stare at loading spinners while fetching massive satellite assets. Pair that with `get_satellite_imagery` to grab raw Sentinel-2 or Landsat captures. Your edge functions handle the heavy lifting, delivering cloud cover percentages and acquisition dates instantly to the frontend.

Soil moisture and weather forecasting

`get_soil_moisture` pulls root zone and surface water levels to dictate irrigation schedules. The AI agent evaluates current saturation and streams immediate watering recommendations to your Vue or Svelte application. Combine that ground truth with `get_weather_forecast`. The tool retrieves 15-day precipitation and temperature models. Your frontend logic updates planting schedules dynamically as the new meteorological data arrives from the MCP Server.

Setup guide

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

Install @ai-sdk/mcp and create an HTTP transport client pointing to the Vinkius endpoint URL. Call mcpClient.tools() and pass the result to streamText.

Yes. Tools like render_index_map return raster image data. The SDK streams this response so your React components can render the visual crop assessment as it arrives.

Your application logic manages the rate limits. The MCP Server processes requests as they come in, so you should implement edge caching for heavy queries like historical weather data.

You get access to over 17 indices including NDVI, NDRE, and MSAVI through the get_vegetation_index tool. The agent selects the correct index based on user prompts about crop health.

Vinkius runs this MCP Server inside an ephemeral V8 Isolate sandbox. When you pass GeoJSON coordinates to register a field, the system processes the location and immediately destroys the memory state. No farm boundaries persist on our infrastructure.

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