
Face Recognition Mcp Server
Wraps the 3DiVi Face SDK Processing Block API as MCP tools so Claude can detect faces, run liveness checks, verify identity, and search galleries without you writing SDK integration code. All nine tools (detect_faces, check_liveness, extract_template, verify_face, search_face, estimate_attributes, estimate_emotion, assess_quality, detect_mask) run on your machine with no cloud dependency. Built for regulated environments where GDPR or BIPA prohibit sending biometric data to third parties. Requires a 3DiVi Face SDK 3.29 license and runs over stdio. The only local biometric MCP option if Azure cloud is off the table for compliance reasons.
- tools
- 9
- last updated
- Apr 14, 2026
Tools
9 toolsPublic tool metadata for what this MCP can expose to an agent.
detect_facesBounding boxes, landmarks, pitch/yaw/roll
Bounding boxes, landmarks, pitch/yaw/roll
No parameter schema in public metadata yet.
check_livenessLiveness verdict + confidence
Liveness verdict + confidence
No parameter schema in public metadata yet.
assess_qualityQuality score, eyes-open flag
Quality score, eyes-open flag
No parameter schema in public metadata yet.
extract_templateContextTemplate (binary, no PII)
ContextTemplate (binary, no PII)
No parameter schema in public metadata yet.
verify_face1:1 similarity score + match verdict
1:1 similarity score + match verdict
No parameter schema in public metadata yet.
search_face1:N ranked match list
1:N ranked match list
No parameter schema in public metadata yet.
estimate_attributesAge, gender, confidence
Age, gender, confidence
No parameter schema in public metadata yet.
estimate_emotion7-class emotion probabilities
7-class emotion probabilities
No parameter schema in public metadata yet.
detect_maskMasked/unmasked verdict
Masked/unmasked verdict
No parameter schema in public metadata yet.
Sponsors
Readme
3DiVi Face SDK — MCP Server
The face recognition MCP server for AI-native development.
On-premise · GDPR-compliant · ISO 30107-3 liveness · No cloud dependency.
What this is
A local Model Context Protocol server that wraps the 3DiVi Face SDK Processing Block API as callable tools. AI coding agents (Claude Code, Cursor, Windsurf, VS Code Copilot) can detect faces, verify identity, run liveness checks, and search a face gallery — without writing a single line of SDK integration code.
All processing runs on the developer's machine. No data leaves the host.
Tools exposed
Details
- Repository
- github.com/cvartel/face-recognition-mcp-server
- Registry
- MCP registry, active