AI Security Matrix

A curated list of AI-enabled security testing tools.

CSPF-Founder/red-clippy

Licence
GPL-3.0
Maintainers
1 contributor · top author wrote 100%
Size
43,545 lines · 133 code files · CI, lockfile
Bundled tools
none found
Shares files with
no overlap found

Before running it

Your right to use, modify or redistribute it is unclear no
The install script is fetched when you run it, so what runs is not the version anyone reviewed no
It sends data to a third party that is not the model provider no
Part of what ships cannot be reviewed by reading the source no
Its container is given access back to the host, so the boundary does not hold no

mcp

Last updatedCategoryToolScopeStarsFlags
★ 3d mcp mpgn/NetExec-mcp
Wraps the NetExec CLI as a subprocess and nothing more, across every protocol it speaks. Discovery meta-tools keep its 128 calls out of the model's context until it asks for them.
 adnetwork 88 none
★ 5d mcp PortSwigger/mcp-server
A Burp Suite extension that opens the running instance to an AI client, so a model can work through the proxy history and replay requests from the session you already have.
 webappapi 1.2k opaque
★ 11d mcp LaurieWired/GhidraMCP
Installs into Ghidra as an extension and opens its decompiler and symbol table to a model, which can rename methods and data as it works through the program.
 binary 11k none
★ 18d mcp zebbern/zebbern-kali-mcp
Ships the Kali toolkit as a container with an HTTP API in front, so the model's commands run in a prepared environment rather than on the machine you started from.
 networkwebapprecon 50 escape
★ 25d mcp mrexodia/ida-pro-mcp
Exposes an open IDA Pro database to an LLM client, so you ask about a binary in chat instead of clicking through the GUI: rename functions, read decompiled code, chase cross-references.
 binary 13k none
50d mcp CSPF-Founder/red-clippy
Holds the engagement record an agent loses when its context fills: the scope, which methodology phases have been covered, and findings with the evidence behind them. The agent tests; this remembers.
 redteamreporting 28 none
63d mcp mwnickerson/bloodhound_mcp
Keeps the tool surface deliberately small, a handful of composite calls plus reference material the model loads only when it needs it, and ships a system prompt with rules about what the graph does and does not prove. Reaches Entra as well as on-premises.
 ad 141 none
79d mcp 0x4m4/hexstrike-ai
Serves a large tool catalogue over MCP and adds a layer of its own that picks which tool to run and with what flags, so the client's model chooses the goal rather than the command line.
 webappnetworkreconbinary 13k none
archived mcp cyproxio/mcp-for-security
One MCP server per security tool, each a thin wrapper over that binary's flags. Development has moved to a successor project under a different name.
 webappnetworkrecon 629 remote
218d mcp Wh0am123/MCP-Kali-Server
A thin bridge giving a model a shell on a Linux box you already run, plus a short list of named tool wrappers. Raw command execution is the point; the wrappers are convenience.
 networkwebapp 857 none
258d mcp GH05TCREW/MetasploitMCP
Drives Metasploit over its RPC interface: search the modules, run an exploit or a post module, generate a payload, and send commands into a session that is already open.
 network 747 none
1.4y mcp MorDavid/BloodHound-MCP-AI
Turns BloodHound's own Cypher query library into one MCP tool per query, so you ask for an attack path in English and the server runs a query someone already wrote and tested.
 ad 383 licence
1.6y mcp atomicchonk/roadrecon_mcp_server
Reads a running ROADrecon instance so a model can question the Entra tenant it already collected, with prompt templates for the analyses people usually run over that data.
 entracloud 53 none
— mcp FuzzingLabs/mcp-security-hub
One hardened container per tool, brought up with Compose, so a job runs only the servers it needs instead of one process holding everything.
 networkwebappbinaryrecon — not checked