How to Use the Face++ / Megvii MCP in Google ADK

Q: How do I configure the Face++ / Megvii MCP Server inside Google ADK?

Instantiate McpToolset using the StreamableHttpServerParameters pointing to your Vinkius endpoint. Pass this toolset to your LlmAgent to let Gemini models call the underlying computer vision tools.

Q: Can I use Gemini's long context to analyze Face++ / Megvii batch results?

Yes. Feed the detailed JSON outputs from getfacesetdetail and multiple comparefaces runs directly into Gemini's context window, allowing the model to find patterns across thousands of face matches.

Q: How do I limit Google ADK access to specific Face++ / Megvii tools?

Use the native toolnames filter when initializing your McpToolset. This restricts the agent to harmless tools like detectface while completely blocking access to modification tools.

Connect Face++ / Megvii to Google ADK using our managed MCP Server to analyze visual datasets directly alongside BigQuery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Face++ / Megvii MCP to Google ADK

Create your Vinkius account to connect Face++ / Megvii to Google ADK 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 Face++ / Megvii with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

BigQuery Biometric Pipelines

The `search_face` tool queries your established FaceSets to match target faces against thousands of records. Your Google ADK agents pull image URLs directly from BigQuery tables and feed them into this tool to run bulk identity resolution. Because Gemini handles huge token contexts, your agent reads entire query histories alongside the results from `get_faceset_detail`. This lets the agent cross-reference matching face tokens with transaction logs in a single reasoning step.

Real-Time Human Body Telemetry

The `detect_body` tool locates human figures in images and returns precise bounding coordinates. Google ADK agents process these coordinates to track physical space occupancy or analyze security camera feeds. You configure the `McpToolset` with your Vinkius HTTP transport URL to expose this MCP Server. The agent combines the body data with `skeleton_detect` results, storing the telemetry directly back into Google Cloud Storage for downstream analytics.

Multi-Face Set Operations

The `create_faceset` tool instantiates a new target database for biometric indexing. Your enterprise agents on Google ADK use this to partition face data by department or security clearance level. The agent populates these partitions using `add_face_to_faceset` based on new employee onboarding events. If an employee leaves, the agent automatically runs `remove_face_from_faceset` to keep your access control lists accurate.

Setup guide

Set up Face++ / Megvii MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Face++ / Megvii tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Face++ / Megvii_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Face++ / Megvii tools via MCP.",
    tools=mcp_tools,
)

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 Face++ / Megvii. 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 Face++ / Megvii 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 Face++ / Megvii MCP in Google ADK

Instantiate `McpToolset` using the `StreamableHttpServerParameters` pointing to your Vinkius endpoint. Pass this toolset to your `LlmAgent` to let Gemini models call the underlying computer vision tools.

Yes. Feed the detailed JSON outputs from `get_faceset_detail` and multiple `compare_faces` runs directly into Gemini's context window, allowing the model to find patterns across thousands of face matches.

Use the native `tool_names` filter when initializing your `McpToolset`. This restricts the agent to harmless tools like `detect_face` while completely blocking access to modification tools.

This MCP Server supports both Stdio and HTTP transports. For enterprise Google Cloud deployments, the HTTP transport is ideal as it connects your containerized agents to the managed Vinkius proxy.

Image payloads and face coordinates are processed in transit through memory-only V8 isolates. No biometric data is written to persistent disk on our servers, and your Megvii API credentials remain fully encrypted within the Vinkius credential manager.

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