How to Use the Face++ / Megvii MCP in VS Code Copilot

Q: How do we share the Face++ / Megvii MCP configuration in VS Code Copilot?

Create a .vscode/mcp.json file in your repository root and add the MCP Server configuration. Commit this file to Git so every developer on your team automatically gains access to the Megvii tools.

Q: Can VS Code Copilot search facial databases using Face++ / Megvii?

Yes, the searchface tool enables your agent to search your FaceSets. It returns the closest matching faces along with confidence scores directly to your active chat.

Q: Does VS Code Copilot support gesture recognition via Face++ / Megvii?

Yes, the gesturedetect tool identifies hand gestures from your input images. Copilot displays the recognized gesture types and coordinate data right in the chat panel.

Q: What details does the face detection tool provide?

The detectface tool returns facial bounding boxes, landmark coordinates, and attributes like age or gender. Your agent parses this structured JSON to build highly detailed user profiles.

Equip your team's VS Code Copilot with Face++ / Megvii vision tools to build facial matchers and body tracking engines.

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 VS Code Copilot

Create your Vinkius account to connect Face++ / Megvii to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Instant face comparisons in Copilot Chat

Use the `compare_faces` tool to measure the similarity between two faces directly within your VS Code Copilot workspace. Your team can run this check to verify Megvii identity verification pipelines using real-time API feedback. This tool allows your agent to write precise verification code based on actual Megvii confidence scores. You eliminate guessing games by letting Copilot call the Megvii API to test your image payloads during development.

Shared FaceSet registry management

Run the `create_faceset` tool to set up a new biometric database group directly from your shared editor session. Your engineering team can manage these Megvii groups collaboratively using the committed workspace configuration. Developers can run `add_face_to_faceset` and `remove_face_from_faceset` to update Megvii reference images on the fly. Executing `get_faceset_detail` lets the agent verify database contents, keeping your VS Code Copilot team synchronized during integration testing.

Team-wide body detection via this MCP Server

Locate human figures and output precise bounding box coordinates inside VS Code Copilot using the `detect_body` tool. This integration gives your team the exact data needed to write spatial tracking and presence detection software using Megvii endpoints. Map physical joints and hand gestures on command by calling `skeleton_detect` and `gesture_detect`. Copilot processes these Megvii coordinate arrays instantly, accelerating the development of interactive human-computer interfaces.

Setup guide

Set up Face++ / Megvii MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Face++ / Megvii MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Face++ / Megvii tools listed. Try asking: "List my recent Face++ / Megvii transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "face-megvii-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 VS Code Copilot

Create a `.vscode/mcp.json` file in your repository root and add the MCP Server configuration. Commit this file to Git so every developer on your team automatically gains access to the Megvii tools.

Yes, the `search_face` tool enables your agent to search your FaceSets. It returns the closest matching faces along with confidence scores directly to your active chat.

Yes, the `gesture_detect` tool identifies hand gestures from your input images. Copilot displays the recognized gesture types and coordinate data right in the chat panel.

The `detect_face` tool returns facial bounding boxes, landmark coordinates, and attributes like age or gender. Your agent parses this structured JSON to build highly detailed user profiles.

Your facial images and FaceSet registries processed by this MCP Server are handled inside a secure, containerized V8 sandbox. Biometric data is never written to disk or stored by Vinkius, maintaining direct, encrypted transit to the Megvii cloud.

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