# eKYC Suite (npm · @wefi-ai/ekyc-suite-mcp)

KYC / eKYC MCP server for face compare, liveness, OCR, and image labeling.

- Trust score: 68/100 (medium)
- Change this week: +22
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@wefi-ai/ekyc-suite-mcp`: 68/100 (this document), [markdown](https://verifymcp.io/servers/wefi-ai-ekyc-suite/wefi-ai-ekyc-suite-mcp.md), [page](https://verifymcp.io/servers/wefi-ai-ekyc-suite/wefi-ai-ekyc-suite-mcp)

## Channel facts

- Registry: `npm`
- Package: `@wefi-ai/ekyc-suite-mcp`
- Version: `1.0.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 86/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 10 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 73/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 907 tokens (~113/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add wefi-ai-ekyc-suite -- npx -y @wefi-ai/ekyc-suite-mcp
```

### Codex

```bash
codex mcp add wefi-ai-ekyc-suite -- npx -y @wefi-ai/ekyc-suite-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "wefi-ai-ekyc-suite": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@wefi-ai/ekyc-suite-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add wefi-ai-ekyc-suite --command npx --arg -y --arg @wefi-ai/ekyc-suite-mcp
```

### Hermes

```yaml
mcp_servers:
  wefi-ai-ekyc-suite:
    command: "npx"
    args: ["-y", "@wefi-ai/ekyc-suite-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "wefi-ai-ekyc-suite": {
      "command": "npx",
      "args": [
        "-y",
        "@wefi-ai/ekyc-suite-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 67, +46)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [functional regression] Security disclosure: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Stability: unverified → 0.20
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional] First check of Schema quality: unverified
- [functional] Licence: MIT

### 2026-07-31 (score 21, −7)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 28, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (8)

### `face_compare` (~127 tokens)

Determine if two photos show the same person by comparing facial features. Returns a similarity score 0-100. Use for: identity verification, duplicate account detection, photo matching. Rate limit: 100 calls per appid (test quota).

Input parameters:

- `photo1` (string, required): First face photo (file path, public URL, or base64)
- `photo2` (string, required): Second face photo for comparison (file path, public URL, or base64)
- `sourcePhotoType` (string): Photo type: 1=watermarked ID photo, 2=HD photo (default)

### `photo_liveness_detect` (~81 tokens)

Check whether a face photo is a genuine capture or has been forged (AI-generated, screen replay, printout, deepfake). Returns risk level 1-3 with attack type classification. Use for: anti-fraud screening, onboarding selfie verification.

Input parameters:

- `file` (string, required): Face photo to analyze (file path, public URL, or base64)

### `video_liveness_detect` (~84 tokens)

Check whether a face video is genuine or a deepfake/replay. Auto-retries on network errors. Returns risk level 1-3 with attack type. Use for: video KYC verification, anti-deepfake screening.

Input parameters:

- `file` (string, required): Face video, max 20s and 20MB (file path, public URL, or base64)

### `id_card_ocr` (~102 tokens)

Extract structured information from a Chinese national ID card photo. Returns name, sex, ethnicity, birth date, ID number, address (portrait side) or issuing authority and validity (emblem side). Use for: customer onboarding, document digitization.

Input parameters:

- `image` (string, required): ID card photo (file path, public URL, or base64)
- `side` (string): 0=portrait side with photo (default), 1=national emblem side

### `bank_card_ocr` (~53 tokens)

Extract card number and expiry date from a bank card front photo. Use for: payment binding, account verification.

Input parameters:

- `image` (string, required): Bank card front photo (file path, public URL, or base64)

### `driver_license_ocr` (~75 tokens)

Extract structured information from a Chinese driver's license (main page only; supplementary page returns error -9005). Returns license number, name, vehicle class, validity dates, etc. Use for: auto insurance, fleet management.

Input parameters:

- `image` (string, required): Driver's license photo (file path, public URL, or base64)

### `vehicle_license_ocr` (~92 tokens)

Extract structured information from a Chinese vehicle license. Supports both main page (plate, VIN, owner) and supplementary page (passenger capacity, inspection records). Use for: auto loans, fleet compliance.

Input parameters:

- `image` (string, required): Vehicle license photo (file path, public URL, or base64)
- `side` (string): 1=main page (default), 2=supplementary page

### `media_labeling` (~293 tokens)

Analyze an image or video for specific attribute labels. Detects portrait attributes (mask, hat, sunglasses, coercion, unconscious, phone, headphones, tattoo, nudity, critical patient, facial mask) and environment attributes (multiple people, inside car, hotel room, car dealership). Async: auto-waits for result. Use for: risk screening, compliance checks, fraud prevention.

Input parameters:

- `doCompare` (string): Enable face consistency check on video: '1'=yes (default), '0'=no
- `doLive` (string): Enable liveness check on video: '1'=yes (default), '0'=no
- `file` (string, required): Image or video to analyze (file path, public URL, or base64)
- `labels` (string, required): Comma-separated label codes, max 5 per request. Portrait: A01(facial mask), A02(medical mask), A04(headphones), A05(nudity), A06(sunglasses), A09(coercion), A10(unconscious), A11(phone), A13(tattoo),…
- `type` (string): 'image' (default) or 'video'

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/wefi-ai-ekyc-suite/wefi-ai-ekyc-suite-mcp#diagnostics

## Score history

- 2026-08-03: 68
- 2026-08-02: 67
- 2026-08-01: 21
- 2026-07-31: 21
- 2026-07-30: 28
- 2026-07-28: 46
- 2026-07-27: 46

## Links

- npm package: https://www.npmjs.com/package/@wefi-ai/ekyc-suite-mcp
- Socket report: https://socket.dev/npm/package/@wefi-ai/ekyc-suite-mcp
- Repository: https://github.com/wefi-ai/eKYC-suite
- Changelog RSS feed: https://verifymcp.io/servers/wefi-ai-ekyc-suite/wefi-ai-ekyc-suite-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/wefi-ai-ekyc-suite/wefi-ai-ekyc-suite-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/wefi-ai-ekyc-suite/wefi-ai-ekyc-suite-mcp