MCP Vulnerability Checker Server

MCP Vulnerability Checker Server

A Model Context Protocol server providing security vulnerability intelligence tools including CVE lookup, EPSS scoring, CVSS calculation, exploit detection, and Python package vulnerability checking.

Category
访问服务器

README

<p align="center"> <img src="logo.png" alt="Vibe tester Logo" width="270"/> </p>

MCP Vulnerability Checker Server

A modular Model Context Protocol (MCP) server providing comprehensive security vulnerability intelligence tools including CVE lookup, EPSS scoring, CVSS calculation, exploit detection, and Python package vulnerability checking.

Demo

<p align="center"> <img src="demo.gif" alt="demo"/> </p>

🔗 Using the Hosted Server

The vulnerability intelligence MCP server is already hosted and ready to use! Simply configure your MCP client to connect to it.

Claude Desktop Configuration

Add this configuration to your Claude Desktop settings file (~/.config/claude/claude_desktop_config.json):

{
  "mcpServers": {
    "vulnerability-intelligence": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-fetch"],
      "env": {
        "FETCH_URL": "https://vulnerability-intelligence-mcp-server-edb8b15494e8.herokuapp.com/sse"
      }
    }
  }
}

Cursor IDE Configuration

Add this configuration to your Cursor MCP settings file (~/.cursor/mcp.json):

{
  "mcpServers": {
    "vulnerability-intelligence": {
      "url": "https://vulnerability-intelligence-mcp-server-edb8b15494e8.herokuapp.com/sse"
    }
  }
}

Alternatively, in Cursor IDE:

  1. Open Cursor Settings → Features → MCP Servers
  2. Click "Add New Server"
  3. Select "Server-Sent Events (SSE)" as the type
  4. Enter URL: https://vulnerability-intelligence-mcp-server-edb8b15494e8.herokuapp.com/sse
  5. Give it a name: vulnerability-intelligence

Test the Connection

Once configured, try these example queries in Claude or Cursor:

  • CVE Lookup: "Look up CVE-2021-44228" (Log4Shell vulnerability)
  • EPSS Score: "Get EPSS score for CVE-2021-44228"
  • Package Check: "Check the 'requests' Python package for vulnerabilities"
  • Exploit Check: "Check for exploits for CVE-2021-44228"
  • CVSS Calculator: "Calculate CVSS score for vector CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H"

🛡️ Available Security Tools

🔍 CVE Vulnerability Lookup (cve_lookup)

  • Purpose: Fetches detailed vulnerability information from the National Vulnerability Database (NVD)
  • Data Source: NIST National Vulnerability Database API 2.0
  • Usage: cve_lookup cve_id="CVE-2021-44228"
  • Features:
    • CVSS scores (v2.0, v3.0, v3.1) with severity ratings
    • Comprehensive vulnerability descriptions
    • References, advisories, and remediation links
    • CWE (Common Weakness Enumeration) mappings
    • Publication and modification timeline
    • Affected product configurations

📊 EPSS Score Lookup (get_epss_score)

  • Purpose: Get Exploit Prediction Scoring System (EPSS) scores for CVEs
  • Data Source: FIRST EPSS API
  • Usage: get_epss_score cve_id="CVE-2021-44228"
  • Features:
    • Probability of exploitation within 30 days
    • AI-powered risk prioritization
    • Real-time threat intelligence integration
    • Percentile rankings for relative risk assessment

🧮 CVSS Score Calculator (calculate_cvss_score)

  • Purpose: Calculate CVSS base scores from vector strings
  • Data Source: CVSS v3.0/v3.1 specification
  • Usage: calculate_cvss_score vector="CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H"
  • Features:
    • Support for CVSS v3.0 and v3.1
    • Detailed metric breakdown
    • Severity level mapping (Critical, High, Medium, Low)
    • Vector string validation and parsing

🔎 Vulnerability Search (search_vulnerabilities)

  • Purpose: Search vulnerability databases with advanced filtering
  • Data Source: Multiple vulnerability databases (NVD, CVE)
  • Usage: search_vulnerabilities keywords="apache" severity="HIGH" date_range="1y"
  • Features:
    • Keyword-based search across vulnerability descriptions
    • Severity filtering (CRITICAL, HIGH, MEDIUM, LOW)
    • Date range filtering (30d, 90d, 1y, 2y, or custom)
    • Advanced query capabilities for threat research

🎯 Exploit Availability Check (get_exploit_availability)

  • Purpose: Check for public exploits and proof-of-concepts (PoCs)
  • Data Source: ExploitDB, Metasploit, GitHub, security advisories
  • Usage: get_exploit_availability cve_id="CVE-2021-44228"
  • Features:
    • Multi-source exploit detection
    • Active exploitation indicators
    • PoC code availability assessment
    • Threat intelligence aggregation

⏰ Vulnerability Timeline (get_vulnerability_timeline)

  • Purpose: Get comprehensive timeline and patch status information
  • Data Source: NVD, vendor advisories, security bulletins
  • Usage: get_vulnerability_timeline cve_id="CVE-2021-44228"
  • Features:
    • Publication and disclosure timeline
    • Patch availability status
    • Vendor advisory tracking
    • Remediation guidance timeline

🎯 VEX Status Check (get_vex_status)

  • Purpose: Check Vulnerability Exploitability eXchange (VEX) status for specific products
  • Data Source: Vendor VEX statements and product security advisories
  • Usage: get_vex_status cve_id="CVE-2021-44228" product="Apache HTTP Server"
  • Features:
    • Product-specific impact assessment
    • Vendor-provided exploitability statements
    • False positive filtering
    • Supply chain impact analysis

📦 Python Package Vulnerability Check (package_vulnerability_check)

  • Purpose: Checks Python packages for known security vulnerabilities
  • Data Source: OSV (Open Source Vulnerabilities) Database + PyPI
  • Usage: package_vulnerability_check package_name="requests" version="2.25.1"
  • Features:
    • Comprehensive vulnerability scanning for PyPI packages
    • Version-specific or all-versions checking
    • Detailed vulnerability reports with severity scores
    • Affected version ranges and fix information
    • Integration with CVE, GHSA, and PYSEC databases
    • Package metadata from PyPI

🏗️ Modular Architecture

The server is built with a clean, modular architecture:

mcp_simple_tool/
├── server.py                    # Main MCP server orchestration
└── tools/                       # Individual tool modules
    ├── cve_lookup.py            # CVE vulnerability lookup
    ├── epss_lookup.py           # EPSS score lookup
    ├── cvss_calculator.py       # CVSS score calculator
    ├── vulnerability_search.py  # Advanced vulnerability search
    ├── exploit_availability.py  # Exploit and PoC detection
    ├── vulnerability_timeline.py # Timeline and patch status
    ├── vex_status.py            # VEX status checking
    └── package_vulnerability.py # Python package security check

tests/                           # Comprehensive test suite
├── run_tests.py                 # Automated test runner
└── test_*.py                    # Individual tool tests

🔧 Alternative Setup Methods

Docker Setup (Recommended for Local Development)

  1. Initial setup:
# Clone the repository
git clone https://github.com/firetix/vulnerability-intelligence-mcp-server
cd vulnerability-intelligence-mcp-server

# Create environment file
cp .env.example .env
  1. Build and run using Docker Compose:
# Build and start the server
docker compose up --build -d

# View logs
docker compose logs -f

# Check server status
docker compose ps

# Stop the server
docker compose down
  1. The server will be available at: http://localhost:8000/sse

  2. Connect to Cursor IDE:

    • Open Cursor Settings → Features
    • Add new MCP server
    • Type: Select "sse"
    • URL: Enter http://localhost:8000/sse

Local Development Setup

  1. Install the uv package manager:
# Install uv on macOS
brew install uv
# Or install via pip (any OS)
pip install uv
  1. Install dependencies and run:
# Install the package with development dependencies
uv pip install -e ".[dev]"

# Using stdio transport (default)
uv run mcp-simple-tool

# Using SSE transport on custom port
uv run mcp-simple-tool --transport sse --port 8000

# Run the comprehensive test suite
python tests/run_tests.py
  1. For Cursor IDE integration (stdio mode):
    • Copy the absolute path to cursor-run-mcp-server.sh
    • Open Cursor Settings → Features → MCP Servers
    • Add new server with "stdio" type and the script path

🧪 Testing the Tools

Run the comprehensive test suite:

# Run all tests
python tests/run_tests.py

# Run individual tool tests
python tests/test_cve_lookup.py
python tests/test_package_vulnerability.py  
python tests/test_modular_server.py

Example Test Outputs

CVE Lookup Test:

🔍 **CVE Vulnerability Report: CVE-2021-44228**

📅 **Timeline:**
   • Published: 2021-12-10T10:15:09.143
   • Last Modified: 2023-11-07T04:10:58.217

⚠️ **CVSS Scores:**
   • CVSS 3.1: 10.0 (CRITICAL)

Package Vulnerability Test:

🚨 **Python Package Security Report: requests**

⚠️ **Found 11 known vulnerabilities**

📦 **Package Information:**
   • Latest Version: 2.32.3
   • Summary: Python HTTP for Humans.

🌍 Environment Variables

Available environment variables (can be set in .env):

  • MCP_SERVER_PORT (default: 8000) - Port to run the server on
  • MCP_SERVER_HOST (default: 0.0.0.0) - Host to bind the server to
  • DEBUG (default: false) - Enable debug mode
  • MCP_USER_AGENT - Custom User-Agent for HTTP requests

🚀 Deploy Your Own Instance

If you want to deploy your own instance of the vulnerability intelligence server, you can use Heroku for quick deployment:

Quick Deploy to Heroku

  1. Click "Deploy to Heroku" button

    Deploy to Heroku

  2. After deployment, your instance will be available at:

    • https://<your-app-name>.herokuapp.com/sse
  3. Configure your MCP client to use your deployed instance:

    • For Claude Desktop: Update the FETCH_URL in your configuration
    • For Cursor IDE: Update the URL in your MCP settings
  4. Test your deployment with the same example queries:

    • CVE Lookup: "Look up CVE-2021-44228"
    • EPSS Score: "Get EPSS score for CVE-2021-44228"
    • Package Check: "Check the 'requests' Python package for vulnerabilities"
    • Exploit Check: "Check for exploits for CVE-2021-44228"

📊 Data Sources & APIs

🤝 Security Use Cases

This MCP server is designed for security engineers, developers, and teams who need:

Vulnerability Research & Intelligence

  • Quick CVE lookups with comprehensive details
  • CVSS and EPSS scoring for accurate risk assessment
  • Advanced vulnerability search across multiple databases
  • Exploit availability and threat intelligence gathering
  • Timeline analysis for understanding vulnerability lifecycle

Risk Assessment & Prioritization

  • EPSS-based exploitation probability scoring
  • CVSS vector calculation and validation
  • VEX status checking for product-specific impact
  • Multi-factor risk analysis combining multiple data sources

Dependency Management

  • Python package security auditing
  • Version-specific vulnerability checking
  • Supply chain security assessment
  • Open source component risk evaluation

Security Operations & Incident Response

  • Rapid vulnerability triage and classification
  • Exploit availability assessment for threat modeling
  • Security advisory research and correlation
  • Timeline-based patch management planning

🔄 Extending the Server

The modular architecture makes it easy to add new security tools:

  1. Create a new module in mcp_simple_tool/tools/
  2. Export the function in tools/__init__.py
  3. Register the tool in server.py
  4. Add tests in tests/

See README_MODULAR.md for detailed extension guide.

📄 License

MIT License - see LICENSE file for details.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选