How to Use the Yitu Technology / 依图科技 MCP in Vercel AI SDK

Q: What kinds of identity checks can Yitu Technology / 依图科技 perform with Vercel AI SDK?

You can run both one-to-one comparisons (comparefaces) and broad searches (searchfaceinrepo). The results for both types of facial recognition are streamed out, letting your agent client react instantly.

Q: Is the data handling secure when using Yitu Technology / 依图科技 with Vercel AI SDK?

The tool supports OAuth via authProvider, allowing you to manage user permissions securely within your Edge Function. This keeps client credentials isolated and manageable.

Q: What data types can be moderated when using Yitu Technology / 依图科技 with Vercel AI SDK?

You use moderateimage to check general content safety for any uploaded picture. This prevents bad or inappropriate media from ever reaching the rest of your application logic.

Real-time face recognition and moderation for Vercel AI SDK UIs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Yitu Technology / 依图科技 MCP to Vercel AI SDK

Create your Vinkius account to connect Yitu Technology / 依图科技 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 Yitu Technology / 依图科技 with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Live Face Detection Results

When a user uploads an image, you can stream the results from `detect_face` directly into your UI. This means users see bounding boxes and face counts appear in real-time, without waiting for a loading spinner. You'll get immediate feedback on every detected face using this tool. It works great with Edge Functions because the data streams out as it's processed.

Verify Identity Against Repositories

You can check if a person is who they say they are by comparing input photos to stored templates using `compare_faces`. This 1:1 verification runs instantly and streams the match confidence back to your frontend. For larger groups, use `search_face_in_repo` to pull top matching candidates. The results stream out as a list of matches with their associated confidence scores.

Anti-Spoofing Check for Liveness

Before accepting an identity, you must confirm the person is real. Use `detect_active_liveness` to perform live action verification on input streams. This tool reports pass/fail status for specific actions taken by the user. If you're dealing with static inputs like photos or screens, use `detect_silent_liveness`. It reliably detects masks and spoofed media, giving your users confidence that the data is genuine.

Setup guide

Set up Yitu Technology / 依图科技 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 Yitu Technology / 依图科技 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 Yitu Technology / 依图科技 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 Yitu Technology / 依图科技. 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 Yitu Technology / 依图科技 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 Yitu Technology / 依图科技 MCP in Vercel AI SDK

The platform sends tool results directly into your UI stream. You don't wait for a final JSON blob; the data appears in real-time as it processes, which is ideal for a smooth user experience.

You can run both one-to-one comparisons (`compare_faces`) and broad searches (`search_face_in_repo`). The results for both types of facial recognition are streamed out, letting your agent client react instantly.

The tool supports OAuth via `authProvider`, allowing you to manage user permissions securely within your Edge Function. This keeps client credentials isolated and manageable.

You use `moderate_image` to check general content safety for any uploaded picture. This prevents bad or inappropriate media from ever reaching the rest of your application logic.

The system processes biometric data, specifically facial features and action metrics, when running `detect_active_liveness`. These results are used to determine if the input source is a live human.

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