REMnux Documentation MCP Server
Enables AI assistants to search and retrieve information from the REMnux malware analysis toolkit documentation, allowing users to ask questions about reverse-engineering tools and get accurate, up-to-date answers from the live documentation.
README
REMnux Documentation MCP Server
An MCP server that lets AI assistants search and retrieve REMnux documentation.
What Is This?
REMnux is a Linux toolkit for reverse-engineering and analyzing malicious software. This MCP server gives AI assistants direct access to REMnux documentation, so you can ask questions about malware analysis tools and get accurate, up-to-date answers.
What it enables:
- Search for tools by name, category, or functionality
- Retrieve detailed information about specific tools
- Answer questions about which REMnux tools to use for particular tasks
Your AI assistant queries the current documentation index rather than relying on potentially outdated training data.
Getting Started
To use this MCP server, add it to your AI tool's configuration. The server is publicly hosted and ready to use.
Claude Desktop
Add to your Claude Desktop configuration file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"remnux-docs": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://docs-mcp.remnux.org/sse"]
}
}
}
Claude Code (CLI)
claude mcp add remnux-docs --transport sse https://docs-mcp.remnux.org/sse
Cursor
Add to .cursor/mcp.json in your project or global settings:
{
"mcpServers": {
"remnux-docs": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://docs-mcp.remnux.org/sse"]
}
}
}
Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"remnux-docs": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://docs-mcp.remnux.org/sse"]
}
}
}
Other MCP-Compatible Tools
For any MCP-compatible AI tool:
- Server URL:
https://docs-mcp.remnux.org/sse - Transport: SSE (Server-Sent Events)
Most tools connect via the mcp-remote npm package, which handles SSE transport.
Example Queries
Once connected, you can ask your AI assistant questions like:
- "What REMnux tools can I use to analyze a suspicious PDF?"
- "How do I extract strings from a malware sample using REMnux?"
- "What's the difference between peframe and pefile?"
- "Which tools in REMnux can deobfuscate JavaScript?"
- "What network analysis tools are available in REMnux?"
The AI will search the REMnux documentation and provide accurate, current information.
MCP Tools
The server exposes these tools to AI assistants:
| Tool | Description |
|---|---|
search_remnux |
Search documentation by keywords |
get_article |
Retrieve full content of a specific article by URL |
get_index_info |
Get index statistics and metadata |
Architecture
This server deploys cloudflare-mcp-for-static-sites, a reusable framework for adding MCP search to any static website. The framework runs on Cloudflare Workers, which simplifies building remote MCP servers by handling transport, authentication, and scaling.
┌─────────────────┐ MCP Protocol ┌─────────────────────┐
│ AI Assistant │◄────────────────────►│ Cloudflare Worker │
│ (Claude, etc.) │ (SSE) │ (MCP Server) │
└─────────────────┘ └──────────┬──────────┘
│
│ Reads
▼
┌─────────────────────┐
│ Cloudflare R2 │
│ (Search Index) │
└─────────────────────┘
▲
│ Generated from
│
┌─────────────────────┐
│ REMnux salt-states │
│ (Source of Truth) │
└─────────────────────┘
Components
Cloudflare Worker — Runs the MCP server at docs-mcp.remnux.org. Handles AI assistant requests using MCP over SSE (Server-Sent Events). Built with Cloudflare's Agents SDK and the McpAgent class in src/index.ts.
Cloudflare R2 — Object storage for the search index. The Worker caches the index in memory for 1 hour to reduce latency.
Search Engine — Powered by Fuse.js for fuzzy matching. Searches across tool names, descriptions, categories, and full content with weighted relevance scoring.
MCP Protocol — Model Context Protocol, an open standard for connecting AI assistants to external data sources.
Search Index Generation
The search index comes from the REMnux salt-states repository, the authoritative source for REMnux tool configurations and documentation.
The generation process:
- The
generate-mcp-index.pyscript in the salt-states CI directory parses tool metadata from the Salt state files - It extracts tool names, descriptions, categories, and documentation URLs
- The script produces a JSON search index conforming to the schema in
src/types.ts - The index is uploaded to the Cloudflare R2 bucket, where the Worker retrieves it
This process runs automatically during REMnux releases. The search index stays synchronized with official tool documentation.
Source Files
This repository contains the REMnux-specific deployment. The Worker code builds on cloudflare-mcp-for-static-sites.
| File | Description |
|---|---|
src/index.ts |
Worker implementation with MCP tool definitions |
src/types.ts |
TypeScript types and Zod schemas for the search index |
wrangler.jsonc |
REMnux-specific Cloudflare Worker deployment configuration |
Development
To run the MCP server locally:
# Install dependencies
bun install
# Start local development server
bun run dev
# Type checking
bun run type-check
# Format and lint
bun run format
bun run lint:fix
For local testing, you'll need a search-index.json file in your R2 bucket. You can generate one using the generate-mcp-index.py script from the salt-states repository.
Contributing
This project is part of the REMnux ecosystem.
- Bug reports and feature requests: Open an issue in this repository
- Code contributions: Submit a pull request with a clear description of changes
- Documentation improvements: PRs welcome for README or code comments
Before submitting code, run bun run type-check and bun run format to ensure consistency.
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。