Metasploit for AI agents: scan, attack, and fix AI agents and MCP servers. Open source security toolkit.
opena2a-org/hackmyagent is an MCP server distributed on github, maintained by opena2a-org, tracked here since June 2026. It has shipped 86 releases and exposes 3 tools. Tools include hackmyagent_benchmark, hackmyagent_deep_scan, hackmyagent_scan. Its composite risk grade is E — an inferred review prompt computed from observed signals, not a verdict. 2 known CVEs on file.
2 advisories published against this server still applies to the version it ships, the most severe rated critical, most recently 2026-08-09.
Reading the source raised one review prompt — dangerous code — each a pattern worth a human look rather than a finding of fault.
full security breakdown →-
hackmyagent_benchmark -
hackmyagent_deep_scan -
hackmyagent_scan
06-15 00:00 07-29 00:00 now
| version | date | src |
|---|---|---|
| v0.32.0 | 2026-08-20 | github |
| v0.31.0 | 2026-08-11 | github |
| v0.30.0 | 2026-08-11 | github |
| v0.29.0 | 2026-08-09 | github |
| v0.28.0 | 2026-08-09 | github |
| v0.27.0 | 2026-08-08 | github |
| v0.26.1 | 2026-08-07 | github |
| v0.26.0 | 2026-08-06 | github |
| v0.25.2 | 2026-08-05 | github |
| v0.25.1 | 2026-07-28 | github |