KYC / eKYC MCP server for face compare, liveness, OCR, and image labeling.
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"io-github-wefi-ai-ekyc-suite": {
"command": "<see-readme>",
"args": []
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Financial-grade identity verification for AI agents. 8 capabilities in one package.
No automated test available for this server. Check the GitHub README for setup instructions.
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
No package registry to scan.
Click any tool to inspect its schema.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in security / finance
Real-time financial market data: stocks, forex, crypto, commodities, and economic indicators
An evil MCP server used for redteam testing
AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.
A Model Context Protocol (MCP) server that provides AI assistants with direct access to the Spreedly payments API. Enables LLMs to manage gateways, process transactions, tokenize payment methods, and more, through structured, validated tool calls.
MCP Security Weekly
Get CVE alerts and security updates for io.github.wefi-ai/ekyc-suite and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
Financial-grade identity verification for AI agents. 8 capabilities in one package.
Upload a photo or video, ask a question, get structured verification results. That's it.
| # | Capability | What you get |
|---|---|---|
| 1 | Face Comparison | Similarity score 0-100 between two face photos |
| 2 | Photo Liveness | Is this photo real or AI-generated/deepfake? (risk level 1-3) |
| 3 | Video Liveness | Is this video real or deepfake? (risk level 1-3) |
| 4 | ID Card OCR | Name, ID number, address from Chinese national ID card |
| 5 | Bank Card OCR | Card number and expiry date |
| 6 | Driver's License OCR | License number, vehicle class, validity dates |
| 7 | Vehicle License OCR | Plate number, VIN, owner, engine number |
| 8 | Media Labeling | 15+ risk attributes: mask, hat, coercion, tattoo, phone, in-car, etc. |
KYC_APPID + KYC_SECRET) → enables capabilities 1-7LABEL_APPID + LABEL_SECRET) → enables capability 8How to get: Tencent Cloud Console (Key A) or contact Huiyan tech support (WeChat: blue-201809) for Key A + Key B.
⚠️ Use TEST credentials (free 100 calls per appid). Production IDs incur charges.
Copy .env.example to .env and fill in your test credentials.
Install this Skill in your AI agent (OpenClaw, etc.), then just talk to it naturally:
| You say | What happens |
|---|---|
| "Compare these two photos — same person?" + upload 2 photos | Returns similarity score (e.g. 96.2/100) |
| "Is this photo AI-generated?" + upload a selfie | Returns risk level 1-3 with attack type classification |
| "Is this video real or deepfake?" + upload a video | Detects deepfake/replay, returns risk level |
| "Read this ID card" + upload ID card photo | Extracts name, ID number, address, ethnicity, birth date |
| "Read this bank card number" + upload bank card photo | Extracts card number and expiry date |
| "Read this driver's license" + upload photo | Extracts license number, name, vehicle class, validity dates |
| "Read this vehicle license" + upload photo | Extracts plate number, VIN, owner, engine number |
| "Check for hat and mask" + upload photo | Detects 15+ risk attributes (see table below) |
The AI agent handles everything automatically — you just upload files and ask questions in natural language.
| Code | Attribute | Use case |
|---|---|---|
| A09 | Under coercion | Anti-fraud: detect if the person is being coerced during identity verification |
| A10 | Unconscious / asleep | Risk alert: detect if the person's eyes are closed or eyelids are being forced open |
| A15 | Critical patient | Loan fraud prevention: flag verification attempts by critically ill individuals |
| A11 | On the phone | Third-party guidance detection: someone may be coaching the user through the process |
| A04 | Wearing headphones | Third-party guidance detection: hidden earpiece coaching during verification |
| A02 | Medical mask | Obstruction: face partially covered, may compromise identity verification accuracy |
| A14 | Wearing hat | Obstruction/disguise: may indicate attempt to alter appearance |
| A06 | Sunglasses | Obstruction: eyes hidden, reduces face recognition confidence |
| A01 | Facial sheet mask | Obstruction: skincare mask covering facial features |
| A05 | Nudity | Compliance: flag inappropriate content during video verification |
| A13 | Tattoo | Risk profiling: visible tattoo detected for feature ma |