Security Intelligence MCP Server

Security Intelligence MCP Server

Provides a unified interface for security analysts to gather threat intelligence from multiple sources including VirusTotal, Shodan, NVD, AnyRun, AlienVault OTX, and GitHub.

Category
访问服务器

README

Security Intelligence MCP Server

A Model Context Protocol (MCP) server that provides a unified interface for security analysts to gather threat intelligence from VirusTotal, Shodan, NVD, AnyRun, AlienVault OTX, and GitHub.

Features

This server implements a set of tools that allow an LLM to perform the following operations:

VirusTotal

  • vt_file_report: Retrieve analysis reports for file hashes (MD5, SHA1, SHA256).
  • vt_url_report: Retrieve analysis reports for URLs.
  • vt_domain_report: Retrieve analysis reports for domains.
  • vt_ip_report: Retrieve analysis reports for IP addresses.

Shodan

  • shodan_host_info: Get detailed host information for a specific IP.
  • shodan_search: Search for hosts matching a specific query.

NVD (National Vulnerability Database)

  • nvd_cve_details: Get detailed information for a specific CVE ID.
  • nvd_search: Search for CVEs using keywords with optional date range filtering (daysBack, pubStartDate/pubEndDate, lastModStartDate/lastModEndDate), pagination (resultsPerPage, startIndex).

AnyRun

  • anyrun_task_details: Get details for a specific sandbox task.
  • anyrun_search: Search for tasks matching a query.
  • anyrun_submit_url: Submit a URL for analysis.
  • anyrun_submit_file: Submit a local file for analysis.
  • anyrun_get_report: Retrieve the final analysis report.

AlienVault OTX

  • otx_indicator_details: Get detailed information for an indicator. Returns all available sections (reputation, geo, malware, url_list, passive_dns, analysis) or a specific section if requested. Supports types: IPv4, IPv6, domain, hostname, file, url.
  • otx_indicator_pulses: Find all OTX Pulses associated with an indicator.
  • otx_pulse_details: Get full details of a specific threat pulse.
  • otx_search_pulses: Search for pulses by keyword.
  • otx_subscribed_pulses: Get your subscribed pulse feed (paginated).
  • otx_recent_activity: Get recent OTX community activity (paginated).

GitHub

  • github_search_advisories: Search GitHub for security advisories and vulnerability discussions.
  • github_search_poc: Search GitHub for exploit PoC code related to a CVE or vulnerability.

Sigma Rule Generator

  • generate_sigma_rules: Generate Sigma detection rules (YAML) from threat indicators. Accepts enriched indicators (IPs, domains, URLs, file hashes, CVEs) with optional descriptions, references, and tags. Supports single mode (all indicators in one rule) or separate mode (one rule per indicator). Configurable severity level, status, and author.

Quick Start Guide

Prerequisites

  • Node.js (v18 or higher)
  • API Keys for the following services:
    • VirusTotal
    • Shodan
    • NVD
    • AnyRun
    • AlienVault OTX
    • GitHub

Installation

  1. Clone the repository or navigate to the project folder:

    cd kb-mcp
    
  2. Install dependencies:

    npm install
    
  3. Configure environment variables: Create a .env file in the root directory and add your API keys:

    VIRUSTOTAL_API_KEY=your_vt_key_here
    SHODAN_API_KEY=your_shodan_key_here
    NVD_API_KEY=your_nvd_key_here
    ANYRUN_API_KEY=your_anyrun_key_here
    ALIENVAULT_OTX_API_KEY=your_otx_key_here
    GITHUB_TOKEN=your_github_token_here
    
  4. Build the project:

    npm run build
    

Running the Server

You can start the server in stdio mode:

npm start

Integration with MCP Clients (e.g., Claude Desktop)

Add the following configuration to your MCP settings file:

{
  "mcpServers": {
    "security-intelligence": {
      "command": "node",
      "args": ["FULL_PATH_TO/kb-mcp/dist/index.js"],
      "env": {
        "VIRUSTOTAL_API_KEY": "your_vt_key",
        "SHODAN_API_KEY": "your_shodan_key",
        "NVD_API_KEY": "your_nvd_key",
        "ANYRUN_API_KEY": "your_anyrun_key",
        "ALIENVAULT_OTX_API_KEY": "your_otx_key",
        "GITHUB_TOKEN": "your_github_token"
      }
    }
  }
}

Alternatively, if your client uses YAML configuration:

mcpServers:
  security-intelligence:
    command: "node"
    args:
      - "FULL_PATH_TO/kb-mcp/dist/index.js"
    env:
      VIRUSTOTAL_API_KEY: "your_vt_key"
      SHODAN_API_KEY: "your_shodan_key"
      NVD_API_KEY: "your_nvd_key"
      ANYRUN_API_KEY: "your_anyrun_key"
      ALIENVAULT_OTX_API_KEY: "your_otx_key"
      GITHUB_TOKEN: "your_github_token"

Architecture

The server uses a provider-based architecture where each security service is encapsulated in its own provider class. This ensures that API-specific logic (authentication, rate limiting, and data formatting) is isolated from the MCP tool definitions.

  • src/index.ts: Main server entry point and tool routing.
  • src/providers/: Individual API clients for each service.
  • src/config.ts: Environment variable management.
  • src/types/: Shared TypeScript interfaces.

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