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

Q: Which tools are best for debating security issues with AutoGen?

The full suite works, but comparing faces (comparefaces) and moderating images (moderateimage) make great debate points. The agents can argue over the certainty of a match or the policy violation.

Build consensus-driven security systems with Yitu Technology / 依图科技 using AutoGen.

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 AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Security Debate and Verification

Set up a group of agents: one acting as Security, another as Operations. When a face is detected via `detect_face`, the Security agent can call `compare_faces` for verification while the Ops agent calls `list_repos` to check if that person should even be in the system. They debate the result until they reach consensus on whether access is granted or denied.

Automated Compliance Checking

You can model a compliance process where one agent runs `moderate_image` and flags policy issues. A second agent then uses `ocr_id_card` to extract mandatory data points, forcing the two agents to cross-reference for full adherence. This multi-agent setup ensures that both image content and document identity are checked before proceeding.

Controlled Repository Changes

Want to delete a face? Don't let one agent do it unilaterally. Use AutoGen to have an 'Approver Agent' debate the need for `remove_face_from_repo` with an 'Auditor Agent,' who first calls `search_face_in_repo` to confirm the identity. This forces deliberation, making your system much more robust than simple linear execution.

Setup guide

Set up Yitu Technology / 依图科技 MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Yitu Technology / 依图科技 tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Yitu Technology / 依图科技_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Yitu Technology / 依图科技 data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Yitu Technology / 依图科技_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Yitu Technology / 依图科技 data")
    print(result.messages[-1].content)

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 AutoGen

It provides a set of specialized tools for the agents to use during debate. Instead of just talking, they can execute concrete actions like facial verification or content moderation via the MCP Server.

You build systems that require consensus. For example, multiple agents might need to agree on whether a face match is valid or if an image is safe after running `detect_silent_liveness`.

The full suite works, but comparing faces (`compare_faces`) and moderating images (`moderate_image`) make great debate points. The agents can argue over the certainty of a match or the policy violation.

The framework handles context passing, allowing agents to use the output of one tool (like `create_face_repo`) as the necessary input for a later debate point or decision.

The agents interact with images, structured identity records, and extracted text. The result of these tools drives the conversation and eventual consensus.

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