How to Use the EyePop.ai MCP in Vercel AI SDK

Stream live object detection data directly into your Vercel AI SDK frontends with the EyePop.ai MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect EyePop.ai MCP to Vercel AI SDK

Create your Vinkius account to connect EyePop.ai 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 EyePop.ai with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time visual data in your UI

Your Vercel AI SDK app can trigger `analyze_image` and `analyze_video` to pull detection results into the browser instantly. The streaming response handles the latency, so your users see bounding boxes and object counts as they arrive. Stop waiting for full request cycles. By integrating this MCP Server, you get granular control over visual data streams without building a custom backend pipeline.

Model management in the browser

Use `list_models` and `get_model` to let your AI client pick the right vision architecture for the current task. Your interface can display available models, letting the end user switch between detection types without a deployment. This setup keeps your frontend logic clean. You query the pipeline state via `get_pop` and modify it on the fly, keeping the visual intelligence tightly coupled to the user experience.

Monitor status without overhead

Call `check_eyepop_status` to ensure your connection is active before sending heavy media payloads. It prevents errors by verifying the API bridge before the AI attempts an expensive analysis task. Your application handles failures gracefully by checking `get_account` metrics. You stay informed about your usage limits and pipeline health through direct tool calls within your existing event loop.

Setup guide

Set up EyePop.ai 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 EyePop.ai 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 EyePop.ai 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 EyePop.ai. 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 EyePop.ai 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 EyePop.ai MCP in Vercel AI SDK

You connect the server as a tool source in your Vercel AI SDK project. Once linked, the AI client exposes the EyePop.ai functions directly to your LLM.

Yes, it processes video frames through the server pipeline. The output streams directly into your application state, keeping your UI responsive under load.

Performance depends on your model choice and stream size. The SDK streams the tool results, which minimizes the perceived wait time for your users.

No. The MCP Server acts as an abstraction layer. You call the tools from your frontend code, and the server handles the API interactions.

Your video and image data are processed through the EyePop.ai pipeline. We only touch the specific media you pass into `analyze_image` or `analyze_video` for detection tasks.

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