mcp-security-server
Provides AI agents with standardized security scanning capabilities for authorized assessments, including host detection, port scanning, service fingerprinting, web vulnerability scanning, CVE verification, and report generation, all with unified JSON output and strict compliance controls.
README
MCP Security Scanner Server v2.0
Professional production-grade MCP Server for security assessment. Powered by Model Context Protocol, built for Kali Linux.
Overview
A professional Model Context Protocol (MCP) Server that provides AI agents with standardized security scanning capabilities. Designed for authorized security assessments with strict compliance controls.
Key Features
- 7-Step Mandatory Flow — Every tool follows: param validation → security filtering → boundary checks → business logic → result packaging → exception capture → logging
- Zero Command Injection — All shell calls use parameter arrays, never string concatenation
- Mandatory Authorization —
legal_authorized=truerequired for all scan operations - 8 CVE Verification — Log4Shell, Spring4Shell, Apache Path Traversal, HTTP/2 Rapid Reset, and more
- Standardized Output — Unified JSON response:
code/msg/target/vuln_list/risk_level/cvss_score/suggest - Professional Logging — Timestamped logs with task IDs, scan trails, and audit records
Architecture
mcp-security-server/
├── server.py # MCP Server Entry Point
├── core/ # Business Logic Layer
│ ├── scanner.py # Scanning Engine (6 tools, 37KB)
│ ├── result.py # Unified Response Builder
│ ├── analyzer.py # CVSS 3.1 Scoring & Vulnerability DB
│ └── reporter.py # Multi-format Report Generator
├── utils/ # Infrastructure Layer
│ ├── executor.py # Safe Command Executor (Parameter Arrays)
│ ├── validator.py # Parameter Validation & Whitelist
│ ├── logger.py # Professional Logging System
│ └── env.py # Kali Environment Detection
└── requirements.txt # Dependencies
Quick Start
1. Install Dependencies
# Python packages
pip3 install mcp pydantic
# System tools (Kali Linux)
sudo apt update && sudo apt install -y nmap curl
2. Start Server
cd mcp-security-server
python3 server.py
3. Configure MCP Client
Add to your MCP client configuration (e.g., Claude Desktop, opencode):
{
"mcpServers": {
"mcp-security-scanner": {
"command": "python3",
"args": ["/path/to/mcp-security-server/server.py"]
}
}
}
Tools
| Tool | Description | Required Params |
|---|---|---|
host_alive_detect |
Host alive detection (ICMP + TCP SYN) | target, legal_authorized |
port_scan |
Port scanning (SYN/Connect) | target, legal_authorized |
service_fingerprint |
Service version detection | target, legal_authorized |
web_vuln_scan |
Web vulnerability scanning | target, legal_authorized |
cve_poc_check |
CVE POC verification | target, legal_authorized, cve_id |
report_generate |
Security report generation | target, legal_authorized, scan_data |
env_check |
Environment & dependency check | (none) |
Usage Examples
Host Alive Detection
{
"target": "192.168.1.1",
"legal_authorized": true,
"timeout": 15
}
Port Scan
{
"target": "192.168.1.1",
"legal_authorized": true,
"ports": "80,443,8080,8443",
"scan_type": "syn"
}
CVE Verification
{
"target": "192.168.1.1",
"legal_authorized": true,
"cve_id": "CVE-2021-44228",
"port": 8080
}
Generate Report
{
"target": "192.168.1.1",
"legal_authorized": true,
"scan_data": "{\"vuln_list\":[...],\"suggest\":[...]}",
"format_type": "html"
}
Supported CVEs
| CVE | Name | CVSS | Verification Method |
|---|---|---|---|
| CVE-2021-44228 | Log4Shell | 10.0 | Java service detection |
| CVE-2022-22965 | Spring4Shell | 9.8 | Spring/Tomcat detection |
| CVE-2023-22515 | Confluence Privilege | 10.0 | Setup endpoint check |
| CVE-2022-26134 | Confluence OGNL | 9.8 | Confluence detection |
| CVE-2021-41773 | Apache Path Traversal | 7.5 | Path traversal test |
| CVE-2021-42013 | Apache Path Traversal 2 | 7.5 | Path traversal test |
| CVE-2023-44487 | HTTP/2 Rapid Reset | 7.5 | HTTP/2 support check |
| CVE-2021-3449 | OpenSSL NULL deref | 5.9 | Version detection |
Standardized Output
{
"code": 0,
"msg": "success",
"target": "192.168.1.1",
"status": "completed",
"scan_data": { ... },
"vuln_list": [
{
"vuln_id": "CVE-2021-44228",
"vuln_name": "Log4Shell",
"cve_id": "CVE-2021-44228",
"cvss_score": 10.0,
"risk_level": "Critical",
"confidence": "Suspected",
"description": "Apache Log4j2 RCE",
"evidence": "Java service detected",
"remediation": "Upgrade Log4j to 2.17.0+"
}
],
"risk_level": "critical",
"cvss_score": 10.0,
"suggest": ["URGENT: Fix critical vulnerability immediately"],
"task_id": "TASK-20260822100000-a1b2c3d4",
"timestamp": "2026-08-22T10:00:00",
"duration": 12.34
}
Logging
Logs are automatically saved to log/ directory:
| Log File | Purpose |
|---|---|
main_YYYY-MM-DD.log |
General operations |
scan_YYYY-MM-DD.log |
Scan activities |
error_YYYY-MM-DD.log |
Errors & exceptions |
audit_YYYY-MM-DD.log |
Security audit trail |
Compliance
This tool is designed for:
- Security assessments with written authorization
- Internal security team vulnerability verification
- Security research and education
PROHIBITED: Unauthorized scanning, data theft, system damage
License
MIT License - Authorized security testing only
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。