Cybersec Toolkit is a Model Context Protocol (MCP) server: Authorization-gated MCP server to discover and run 670+ security tools for CTF, pentest, and DFIR. In practice that means any MCP-compatible AI assistant can call Cybersec Toolkit's tools directly — the model decides when to use them in a conversation or agent run.
It runs locally: the Docker image ghcr.io/26zl/cybersec-toolkit:1.1.1 speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v1.1.1, published under the MIT license, with source at 26zl/cybersec-toolkit on GitHub, where it has earned 48 stars.
Cybersec Toolkit is listed under Security on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Cybersec Toolkit for 26zl, claim this listing to verify ownership, earn the Verified badge, and keep the details current.
▸Docker image — ghcr.io/26zl/cybersec-toolkit:1.1.1 · MCP over stdio
▸Open source — MIT license · 26zl/cybersec-toolkit