# AIShield Security Scanner (npm · aishield-mcp-server)

Scans MCP servers for tool poisoning, prompt injection and supply chain risks.

- Trust score: 82/100 (high trust)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-11

## Components

- remote · `aishield.tools`: 57/100, [markdown](https://verifymcp.io/servers/lm203688-aishield/api-v1-mcp.md), [page](https://verifymcp.io/servers/lm203688-aishield/api-v1-mcp)
- npm · `aishield-mcp-server`: 82/100 (this document), [markdown](https://verifymcp.io/servers/lm203688-aishield/aishield-mcp-server.md), [page](https://verifymcp.io/servers/lm203688-aishield/aishield-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `aishield-mcp-server`
- Version: `4.2.2`
- 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 2026-08-11.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 30 of 96 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to lm203688/aishield).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 3 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 78/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 635 tokens (~105/item across 6 items; 6 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 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 lm203688-aishield -- npx -y aishield-mcp-server
```

### Codex

```bash
codex mcp add lm203688-aishield -- npx -y aishield-mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "lm203688-aishield": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "aishield-mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add lm203688-aishield --command npx --arg -y --arg aishield-mcp-server
```

### Hermes

```yaml
mcp_servers:
  lm203688-aishield:
    command: "npx"
    args: ["-y", "aishield-mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "lm203688-aishield": {
      "command": "npx",
      "args": [
        "-y",
        "aishield-mcp-server"
      ]
    }
  }
}
```

## 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.

### 2026-08-11 (score 82, +6)

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

### 2026-08-09 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-07 (score 75, +5)

- [security regression] Known CVEs: partial → unverified
- [security improvement] Known CVEs: partial → pass
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Dependency health: partial → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Stability: unverified → 0.07
- [functional] Dependency health: partial → 0.85
- [functional] Package version: 4.2.1 → 4.2.2

### 2026-08-06 (score 70, +24)

- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: fair
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 100

### 2026-08-05 (score 46)

First indexed and scored.

## MCP tools (6)

### `aishield_scan` (~151 tokens)

AIShield安全扫描 — 扫描MCP Server/AI工具的安全风险。

对齐OWASP MCP Top 10 (2025 v0.1) 与 Agentic AI Top 10，201条规则覆盖两套风险分类。
5维评分: 安全(40%)/权限(20%)/数据处理(20%)/供应链(10%)/可靠性(10%)
返回: 评分 + 风险等级 + OWASP合规矩阵 + 修复建议

Input parameters:

- `name` (string): Tool name (optional)
- `source_url` (string, required): GitHub repo URL of the tool to scan
- `tool_type` (string): Tool type

### `aishield_guardrail` (~96 tokens)

AIShield安装前安全检查 — 在安装任何MCP/AI工具前调用此工具。

返回pass/block判定 + 评分 + OWASP合规矩阵。
建议在安装任何第三方MCP Server前自动调用此工具。

Input parameters:

- `auto_block` (boolean): If true, return block verdict for unsafe tools
- `source_url` (string, required): GitHub repo URL of the tool to check

### `aishield_prompt_check` (~96 tokens)

Prompt安全检测 — 检测用户输入的Prompt是否存在注入/越狱/数据外传风险。

支持中文和英文，覆盖: 越狱指令/身份切换/系统提示窃取/数据外传/角色扮演注入/零宽字符/Unicode编码

Input parameters:

- `prompt` (string, required): 待检测的Prompt文本（至少10个字符）

### `aishield_banned_words` (~96 tokens)

中文违禁词检测 — 检测文本中的违禁词/敏感词。

覆盖6大平台: 微信/抖音/小红书/B站/知乎/微博
返回: 违禁词列表 + 法律条文 + 罚款金额 + 替换建议

Input parameters:

- `platform` (string): 目标平台
- `text` (string, required): 待检测文本

### `aishield_rug_pull` (~91 tokens)

Rug Pull检测 — 检查MCP工具是否在版本更新中移除安全代码或新增可疑网络请求。

对比最近commit diff，检测: 安全代码删除、新增网络请求、权限扩大、大量代码删除。
返回风险等级(critical/high/medium/low/safe)和具体发现。

Input parameters:

- `source_url` (string, required): GitHub repo URL

### `aishield_handshake` (~105 tokens)

MCP握手验证 — 分析MCP配置、检测npx自动安装风险、敏感环境变量、工具描述异常长度。

提取README/package.json中的MCP配置，分析: npx -y风险、敏感env变量、远程URL安全性、
工具描述长度（>500字符可能隐藏指令）。如果是HTTP类型MCP，尝试实际握手。

Input parameters:

- `source_url` (string, required): GitHub repo URL

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/lm203688-aishield/aishield-mcp-server#diagnostics

## Score history

- 2026-08-11: 82
- 2026-08-10: 76
- 2026-08-09: 76
- 2026-08-08: 75
- 2026-08-07: 75
- 2026-08-06: 70
- 2026-08-05: 46

## Links

- npm package: https://www.npmjs.com/package/aishield-mcp-server
- Socket report: https://socket.dev/npm/package/aishield-mcp-server
- Repository: https://github.com/lm203688/aishield
- Website: https://aishield.tools/
- Changelog RSS feed: https://verifymcp.io/servers/lm203688-aishield/aishield-mcp-server.xml
- Changelog JSON feed: https://verifymcp.io/servers/lm203688-aishield/aishield-mcp-server.json
- HTML version of this page: https://verifymcp.io/servers/lm203688-aishield/aishield-mcp-server