A Model Context Protocol (MCP) server built with FastMCP to provide AI models with structured technical data about rootkit techniques and families.
View on GitHub ↗A Model Context Protocol (MCP) server built with FastMCP to feed your AI model technical data about rootkit techniques, rootkit and bootkit families from the Rootkit Techniques Matrix. Consists of two files: server.py and matrixdata.json. The latter stores data from the matrix in a format understandable for the methods in server.py.
It's compatible with Open WebUI and Claude Windows app. Since I don't have access to Claude, I tested it on a locally deployed model Ollama + Qwen3:8b. But compatibility with Claude was added as well. I don't use Linux, so everything was tested on Windows.
The server itself doesn't need configuration. You simply run it as python server.py. If you are running a local model setup (Ollama + Open WebUI), follow these steps to connect Open WebUI to your MCP server (Ollama app itself can't be directly connected to the MCP server).
1. Install Ollama app and choose (download) qwen3:8b model.
2. Now we need to install the Open WebUI framework and connect it to the Ollama service. But since Open WebUI is only compatible with Python 3.11, we need to install Docker Desktop for Windows to create a virtual environment for it. Once installed, run the following command to create the environment.
3. Run the container or make sure it's running.
5. Now, we can setup the server. Go to http://localhost:3000/. Navigate to: Your profile icon - Admin panel - Settings - Integration - External Tool Servers - Add connection. Type: MCP (Streamable HTTP) Name: rkmatrix ID: rkmatrix URL: http://host.docker.internal:8000/mcp Auth: None
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/ArtemBaranov--rkmatrix-mcp-server.html)
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is
zhuyansen/new-term-radarDaily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps before keyword tools list them.
yzg1226/mcd-party-officer🍟 麦当劳门店派对成团调度 Skill — 把派对从「策划」推进到「办得成」：成团概率雷达 / 包场vs拼团 / 择日黄历 / 儿童营养指数 / 招募卡与邀请函
fellowgeek/mcp-memoryAn OKF-backed Model Context Protocol (MCP) server delivering persistent long-term memory and SQLite FTS5 search for AI agents.
hirotomasato/yowesGenerate realistic teacher documents (ID cards, licenses, letters) for 13 countries via MCP.
hujjun/mcd-saver-strategist麦当劳省钱点餐助手（麦门精算师）｜麦当劳优惠券组合优化 Skill：拉取麦当劳菜单与全部可用优惠券，算出最省的点餐组合，巨无霸套餐 ¥47 → ¥21.9（省 53%）。McDonalds MCP（麦当劳 MCP）coupon optimizer · McDonalds China MCP Server · Agent Skill for WorkBuddy · 麦当劳程序员创意开发大赛参赛作品
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.