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

Q: What identity checks can Yitu Technology / 依图科技 perform with Mastra AI?

You can sequence tasks like reading an ID card (ocridcard), detecting a face, and then verifying that face against a repository using comparefaces. The whole chain runs as one cohesive workflow.

Q: Does Yitu Technology / 依图科技 support human review with Mastra AI?

Yes. You can use the requireToolApproval setting in your Mastra AI client definition. This forces your automated process to pause and wait for a human agent to manually approve or deny the result before continuing.

Automating compliance checks with Mastra AI using facial recognition tools.

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 Mastra AI

Create your Vinkius account to connect Yitu Technology / 依图科技 to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute Complex Identity Verification

Build multi-step processes that require verification, like checking an ID card and then comparing the face. You can first run `ocr_id_card` to extract data, and immediately follow up by running `compare_faces` against that identity. Mastra AI handles failures gracefully here. If the initial OCR step fails or the comparison times out, your workflow engine can automatically retry with different credentials or notify an admin.

Manage Facial Templates Reliably

The framework allows you to build scheduled jobs for identity management. You can use `list_repos` to check which repositories exist before attempting a new registration via `create_face_repo`. This prevents workflow errors. If an employee leaves, your automated process calls `remove_face_from_repo` and logs the action, ensuring data cleanup is handled reliably even if the initial deletion attempt fails.

Detect Fraud Using Liveness Checks

When a user submits credentials, you must ensure they aren't using deepfakes. Your workflow calls `detect_silent_liveness` to check for photos or masks before proceeding with any transaction. If the silent liveness fails, your Mastra AI workflow triggers an alternate path—maybe sending the request to manual human review—instead of letting the payment attempt fail entirely.

Setup guide

Set up Yitu Technology / 依图科技 MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Yitu Technology / 依图科技 tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "yitu-technology-mcp-client",
  servers: {
    "yitu-technology-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Yitu Technology / 依图科技 Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Yitu Technology / 依图科技 tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Yitu Technology / 依图科技 transactions"
);
console.log(result.text);

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 Mastra AI

Mastra AI's built-in workflow engine manages conditional branching and automatic retries. You can define complex paths, such as 'if OCR fails, then wait 5 minutes and try again.'

You can sequence tasks like reading an ID card (`ocr_id_card`), detecting a face, and then verifying that face against a repository using `compare_faces`. The whole chain runs as one cohesive workflow.

Yes. You can use the `requireToolApproval` setting in your Mastra AI client definition. This forces your automated process to pause and wait for a human agent to manually approve or deny the result before continuing.

The server handles various biometric inputs, including facial templates stored in repositories, and extracted text data from ID cards. Both types of structured data can be used to govern your workflow.

You can automate the full lifecycle: creating repositories, adding faces (`add_face_to_repo`), running liveness checks, and finally searching for a face across all stored records.

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