Face++ / Megvii Connector for AI agents.
10 live capabilities
Automate facial recognition and identity verification for your business.
Waiting for input…
Why people use Face++ / Megvii
Face++ / Megvii: Automated Identity Verification for Security Teams
This Connector changes that by letting your agent do the heavy lifting. You just point your agent at a folder of images or a URL, and it handles the detection and comparison. You get a clear summary of who's who and how they felt, all without leaving your workspace.
What Vinkius changes
You get industrial-grade vision capabilities without leaving your chat interface.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Automated Identity Verification
A compliance officer asks the agent to compare a driver's license photo against a selfie using compare_faces to flag potential fraud.
- Real-world use case 02
UX Emotion Analysis
A researcher asks the agent to detect emotions and gestures in a series of user testing photos using detect_face and gesture_detect.
- Real-world use case 03
Security Feed Monitoring
A security lead asks the agent to find all human bodies in a series of security photos using detect_body.
Complete set · 10capabilities
The complete Face++ / Megvii capability set.
These are the exact actions your AI can choose when you ask it to work with Face++ / Megvii.
01—04
4 capabilities in this set.
Part of 10 available through Face++ / Megvii.
- 01 Capability
Gesture detect
Recognize specific hand movements from a photo. It's great for analyzing interaction cues.
- 02 Capability
Get faceset detail
Pull all the data associated with a specific face database. Use this to audit your records.
- 03 Capability
Remove face from faceset
Delete a face from your searchable records. Keep your database clean and up to date.
- 04 Capability
Search face
Find a specific person within a FaceSet. This lets your agent perform rapid lookups in large sets.
05—07
3 capabilities in this set.
Part of 10 available through Face++ / Megvii.
- 05 Capability
Create faceset
Set up a new database for face matching. Use this to organize different groups of people.
- 06 Capability
Detect body
Find human bodies within an image. This is the first step for posture or crowd analysis.
- 07 Capability
Detect face
Locate faces and identify key attributes. It pulls out data like age and emotion automatically.
08—10
3 capabilities in this set.
Part of 10 available through Face++ / Megvii.
- 08 Capability
Skeleton detect
Map out human skeletons to analyze posture. It provides the keypoints needed for movement analysis.
- 09 Capability
Add face to faceset
Add a specific face to a searchable database. This helps build your library of known identities.
- 10 Capability
Compare faces
Check if two different images show the same person. It returns a confidence score for the match.
Set up in minutes
One URL. Then ask Face++ / Megvii to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Face++ / Megvii from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_9XeNBogqnvbfe37ielQPllFDO6AZEm0YUpuNS984/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Face++ / Megvii, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Face++ / Megvii for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_9XeNBogqnvbfe37ielQPllFDO6AZEm0YUpuNS984/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Face++ / Megvii URL.
- Step 03
Save and start
Save the connection and enable Face++ / Megvii in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"face-megvii": {
"url": "https://edge.vinkius.com/vk_preview_9XeNBogqnvbfe37ielQPllFDO6AZEm0YUpuNS984/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Face++ / Megvii
Open Agent mode in chat and ask: "Using Face++ / Megvii, help me...". 10 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"face-megvii": {
"url": "https://edge.vinkius.com/vk_preview_9XeNBogqnvbfe37ielQPllFDO6AZEm0YUpuNS984/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Face++ / Megvii
Ask Copilot: "Using Face++ / Megvii, help me...". 10 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"face-megvii": {
"url": "https://edge.vinkius.com/vk_preview_9XeNBogqnvbfe37ielQPllFDO6AZEm0YUpuNS984/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Face++ / Megvii
Open Cascade and ask: "Using Face++ / Megvii, help me...". 10 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"face-megvii": {
"url": "https://edge.vinkius.com/vk_preview_9XeNBogqnvbfe37ielQPllFDO6AZEm0YUpuNS984/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Face++ / Megvii
Ask Cline: "Using Face++ / Megvii, help me...". 10 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add face-megvii --transport http "https://edge.vinkius.com/vk_preview_9XeNBogqnvbfe37ielQPllFDO6AZEm0YUpuNS984/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Face++ / Megvii
Ask Claude: "Using Face++ / Megvii, show me...". 10 tools are ready
Where the request belongs
Work Face++ / Megvii can move forward.
This is for security professionals handling high-volume identity checks, UX researchers studying human behavior, and developers who need to skip building their own computer vision models.
Compliance Officer
Automating KYC checks by asking the agent to verify IDs against live selfies.
UX Researcher
Analyzing user frustration and hand gestures during product testing by batch processing photos.
Computer Vision Engineer
Integrating high-accuracy face and body detection into existing workflows without writing custom models.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsEyePop.ai
Add computer vision to your apps with pre-trained models for object detection, face recognition, and image classification.
NVIDIA Vision
Generate images, analyze visuals, detect objects, and caption images via NVIDIA Vision APIs.
ThisPersonDoesNotExist
Generate realistic, high-resolution faces of non-existent people using StyleGAN2 for design, mockups, and privacy-focused personas.
SigmaMind AI
Train custom computer vision models with your own images and deploy object detection and classification without ML expertise.
Hugging Face Vision
Connect Hugging Face Vision to any AI agent via MCP.
Tencent Youtu / 腾讯优图
China's leading computer vision platform. perform facial recognition, analysis, and liveness checks via AI.
Bring your own AI
Change the model, client or framework. Keep Face++ / Megvii connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Face++ / Megvii.
The practical details behind the request, access and result.
What is Face++ / Megvii?
It is a professional-grade facial recognition and computer vision platform. It allows your AI agent to perform advanced tasks like identity verification and emotion analysis.
Can Face++ / Megvii do KYC?
Yes, it is commonly used for KYC. Your agent can compare a person's live selfie against their official ID to verify their identity.
Can I use Face++ / Megvii for emotion detection?
Yes, the Connector can detect faces and pull out attributes like mood and emotion, which is great for analyzing user reactions.
Does Face++ / Megvii support body tracking?
Yes, it includes skeleton detection which maps out human body keypoints, allowing for posture and movement analysis.
How do I connect Face++ / Megvii to Claude?
You can connect it easily through the Vinkius catalog. Just subscribe, add your API keys, and your agent will have access to all the vision capabilities.
Is Face++ / Megvii good for large databases?
Yes, it uses FaceSets which are specifically designed to manage and search through large-scale databases of faces efficiently.
How do I find my Face++ API Key and Secret?
Log in to the Face++ Console, go to [Dashboard] -> [API Key], and you will find your unique Key and Secret there. Ensure you have the necessary permissions enabled.
Can I analyze images from a local file?
This server currently supports analysis via image_url. To use local files, you should upload them to a public or private storage and provide the resulting URL to the capabilities.
What attributes can be returned during face detection?
Common attributes include gender, age, emotion, head pose, smile, face quality, and skin status. You can specify these in the return_attributes parameter of the detect_face capability.
One connection away
Give your agent a direct line to Face++ / Megvii.
Connect Face++ / Megvii once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available