13 tagged penetration-testing, measured the same way as everything else here.
Browse within: ctf 7offensive-security 7red-team 7
MCP server Claude CodeCodexCursor +2
One of 7 in .mcp.json
MCP server "skill-router" as configured in blacklanternsecurity/red-run. Runs locally from the tools/skill-router Python package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
MCP server "keysmcp", hosted remotely at 127.0.0.1, as configured in truststrikelabs/BrokenMCP. Needs 2 environment variables to run.
Xiangyu-Li97/prompt-injection-mcp
MCP server Claude CodeCodexCursor +2
MCP server "prompt-injection-mcp" as configured in Xiangyu-Li97/prompt-injection-mcp. Runs locally from the prompt-injection-mcp npm package.
MCP server Claude CodeCodexCursor +2
MCP server "NeuralReaper" as configured in the-artist111/NeuralReaper. Launched with C:\Program Files\Docker\Docker\resources\bin\docker.exe run --rm -i --network ho.
MCP server Claude CodeCodexCursor +2
MCP (stdio JSON-RPC) server for Pentool AI — local LLM assistant for pentest. Runs locally from the pentool-mcp-server Python package.
securityscan-api/securityscan-mcp
MCP server Claude CodeCodexCursor +2
Unified MCP server — give your AI agent the ability to secure its own environment. Runs locally from the securityscan-mcp Python package.
onsecurity/onsecurity-mcp-server
MCP server Claude CodeCodexCursor +2
MCP server "onsec-mcp" as configured in onsecurity/onsecurity-mcp-server. Runs locally from the onsec-mcp npm package.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: