10 intentionally malicious MCP servers that exploit protocol features to attack AI clients. For security research and defense testing.
Cross-referenced across 55 tracked directories
#45839
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
2/9/2026
Created
9
GitHub Stars
1
Forks
2/9/2026
Last Commit
Recently added to the ecosystem
sinewaveai
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis, auto-fix.
...moresjkim1127
A security-first MCP server empowering AI agents to orchestrate Ghidra, Radare2, and YARA for automated reverse engineering.
...morehybridindie
Secure MCP server for ComfyUI with workflow inspection and audit logging
Anton Areso Gladyshev <[email protected]>
A secure and scoped SSH Model Context Protocol (MCP) server for executing safe, read-only diagnostic commands only