Security Scanner MCP Server
Multi-engine container and system vulnerability scanning for AI agents. Wraps Trivy and Grype with cross-engine validation, SBOM generation, and IaC misconfiguration scanning.
README
Security Scanner MCP Server
Multi-engine container & system vulnerability scanning for AI agents. Wraps Trivy and Grype with cross-engine validation, SBOM generation, and IaC misconfiguration scanning.
Why This Exists
Most security MCP servers wrap a single scanner. This one wraps two — Trivy (Aqua Security) and Grype (Anchore) — and runs them against the same target to surface what each engine catches alone. Different vulnerability databases + different detection logic = broader coverage.
Key differentiator: No other MCP server offers multi-engine cross-validation.
Features
- 15 tools covering vulnerability scanning, SBOM generation, IaC checks, and database management
- Cross-engine validation — run Trivy + Grype on the same image and see what each catches alone
- MIT licensed — no AGPL encumbrance (unlike
@aikidosec/mcp) - npm-native — install via
npx, works with Claude Desktop, Cursor, and any MCP client - No cloud account required — runs locally against Docker daemon or filesystem
Quick Start
🚀 New here? See the Quick Start Guide — get scanning in under 5 minutes.
Prerequisites
Install at least one scanning engine:
# Trivy (recommended)
curl -sfL https://raw.githubusercontent.com/aquasecurity/trivy/main/contrib/install.sh | sh -s -- -b /usr/local/bin
# Grype (for cross-validation)
curl -sSfL https://raw.githubusercontent.com/anchore/grype/main/install.sh | sh -s -- -b /usr/local/bin
Claude Desktop / Cursor
Add to your MCP configuration:
{
"mcpServers": {
"security-scanner": {
"command": "npx",
"args": ["-y", "@supernova123/security-scanner-mcp-server"]
}
}
}
Standalone
npx @supernova123/security-scanner-mcp-server
Tools
| # | Tool | Engine | Description |
|---|---|---|---|
| 1 | scan_image |
Trivy | Scan Docker image for vulnerabilities |
| 2 | scan_image_grype |
Grype | Same target via Grype (cross-validation) |
| 3 | vulnerability_report |
Trivy | Detailed report with remediation |
| 4 | scan_filesystem |
Trivy | Local dir/file vulnerability + misconfig scan |
| 5 | scan_filesystem_grype |
Grype | Cross-engine filesystem scan |
| 6 | scan_repository |
Trivy | Remote git repo scan |
| 7 | scan_remote_image |
Grype | Pull from registry directly (no Docker daemon) |
| 8 | scan_purl |
Grype | Single Package URL vulnerability lookup |
| 9 | scan_sbom |
Trivy | Scan SBOM file for vulnerabilities |
| 10 | generate_sbom |
Trivy | Generate CycloneDX/SPDX SBOM |
| 11 | scan_config |
Trivy | IaC misconfiguration scan |
| 12 | cross_validate |
Both | Run both engines, surface divergence |
| 13 | db_status |
Grype | Check vulnerability DB status |
| 14 | update_db |
Grype | Update vulnerability database |
| 15 | get_version |
Both | Engine version + availability |
Cross-Validation Example
The cross_validate tool runs both Trivy and Grype on the same Docker image and compares results:
{
"combined_summary": {
"total_unique_cves": 47,
"critical": 2,
"high": 8,
"medium": 23,
"low": 14
},
"divergence": {
"only_in_trivy_count": 5,
"only_in_grype_count": 3,
"severity_mismatches": 2,
"only_in_trivy": ["CVE-2023-1234", ...],
"only_in_grype": ["CVE-2023-5678", ...]
},
"insight": "Cross-validation found 5 CVEs only in Trivy and 3 only in Grype. Using both engines gives broader coverage than either alone."
}
Competitive Landscape
| Package | Engine | License | Weekly Downloads |
|---|---|---|---|
@aikidosec/mcp |
Cloud API | AGPL-3.0 | ~11,800 |
@paretools/security |
Trivy + Semgrep | MIT | ~75 |
@supernova123/security-scanner-mcp-server |
Trivy + Grype | MIT | TBD |
aquasecurity/trivy-mcp |
Trivy (Go plugin) | MIT | N/A (not npm) |
anchore/grype-mcp |
Grype (Python) | Apache-2.0 | N/A (not npm) |
Development
git clone https://github.com/friendlygeorge/security-scanner-mcp-server.git
cd security-scanner-mcp-server
npm install
npm run build
npm test
License
MIT — see LICENSE
Links
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。