# Face++ / Megvii MCP for AI Agents AI Agent Connect > Face++ / Megvii is a facial recognition and computer vision MCP that lets your AI agent handle identity verification, emotion analysis, and body tracking. It turns complex visual data into actionable info without you having to manually navigate a web console or manage messy image files. ## Overview - **Category:** image-video - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_9XeNBogqnvbfe37ielQPllFDO6AZEm0YUpuNS984/ai-agent-connect - **Tags:** computer-vision, facial-recognition, identity-verification, biometrics, image-analysis, gesture-detection ## Description You can finally stop jumping between browser tabs to run image analysis. This Connector connects your AI agent directly to Face++, the heavy hitter in facial recognition. Instead of manually uploading photos to a web console to see if two people are the same, you just ask your agent to do it. It handles the heavy lifting of identity verification, emotion detection, and body tracking in the background. If you're running a KYC audit or trying to map out human gestures in a UX study, your agent just pulls the data and gives you the answer. It's one of the easiest ways to bring industrial-grade computer vision into your daily workflow through the Vinkius catalog. You get to stay in your coding environment or chat window while the agent does the gritty work of searching face databases and analyzing human skeletons. ## Tools ### gesture_detect Recognize specific hand movements from a photo. It's great for analyzing interaction cues. ### get_faceset_detail Pull all the data associated with a specific face database. Use this to audit your records. ### remove_face_from_faceset Delete a face from your searchable records. Keep your database clean and up to date. ### search_face Find a specific person within a FaceSet. This lets your agent perform rapid lookups in large sets. ### create_faceset Set up a new database for face matching. Use this to organize different groups of people. ### detect_body Find human bodies within an image. This is the first step for posture or crowd analysis. ### detect_face Locate faces and identify key attributes. It pulls out data like age and emotion automatically. ### skeleton_detect Map out human skeletons to analyze posture. It provides the keypoints needed for movement analysis. ### add_face_to_faceset Add a specific face to a searchable database. This helps build your library of known identities. ### compare_faces Check if two different images show the same person. It returns a confidence score for the match. ## Prompt Examples **Prompt:** ``` Look at this photo and tell me if the person looks happy. ``` **Response:** ``` I've analyzed the image. Here is the breakdown: | Attribute | Result | | :--- | :--- | | **Face Detected** | Yes (1) | | **Gender** | Female | | **Estimated Age** | 28 | | **Emotion** | Happy | Would you like to see the confidence score for the emotion detection? ``` **Prompt:** ``` Compare these two IDs. Are they the same person? ``` **Response:** ``` I've compared the faces from both images. * **Confidence Score:** 98.5% * **Match Status:** Confirmed This is well above the recommended threshold for matching identities. ``` **Prompt:** ``` Find the person in this folder who is waving. ``` **Response:** ``` I've scanned the images in your folder using gesture detection. I found one match: * **Image:** `user_test_04.jpg` * **Gesture:** Waving * **Emotion:** Neutral Would you like me to analyze the skeleton keypoints for this image as well? ``` ## Capabilities ### Verify identities Compare two different images to see if they belong to the same person with a confidence score. ### Extract facial attributes Detect faces in photos and get data on age, gender, and current emotions. ### Search face databases Query existing face collections to find specific individuals quickly. ### Track human skeletons Map out body keypoints to analyze posture and movement in images. ### Identify hand gestures Detect and categorize specific hand movements from image data. ### Manage face collections Create, update, and organize searchable face databases for large scale matching. ## Use Cases ### 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. ### 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. ### Security Feed Monitoring A security lead asks the agent to find all human bodies in a series of security photos using detect_body. ### Biometric Database Management A power user asks the agent to create a new database and add 50 faces to it using create_faceset and add_face_to_faceset. ## Benefits - Automate KYC workflows by using compare_faces to instantly flag identity mismatches without manual review. - Get deeper insights into user behavior by using gesture_detect and detect_face to analyze emotions during testing. - Manage large-scale biometric data easily with create_faceset and search_face for rapid lookups. - Simplify posture analysis by using skeleton_detect to track human movement without manual labeling. - Reduce manual data entry by using add_face_to_faceset to build your database via natural language queries. ## How It Works The bottom line is you get industrial-grade vision capabilities without leaving your chat interface. 1. Subscribe to the Face++ / Megvii MCP on Vinkius. 2. Enter your Face++ API Key and API Secret into your AI client settings. 3. Ask your agent to analyze images, compare faces, or search your face databases. ## Frequently Asked Questions **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 tools. **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](https://console.faceplusplus.com.cn/), 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 tools. **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` tool.