45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
KevinRabun/judges is an MCP server distributed on github, maintained by KevinRabun, tracked here since June 2026. It has shipped 0 releases and exposes 32 tools. Tools include analyze_dependencies, benchmark_gate, evaluate_app_builder_flow, evaluate_batch, evaluate_code, evaluate_code_single_judge, and 26 more. Its composite risk grade is C — an inferred review prompt computed from observed signals, not a verdict.
Reading the source raised 2 review prompts — dangerous code and toxic flow (lethal trifecta) — each a pattern worth a human look rather than a finding of fault.
Since the previous scan on 2026-09-01: 31 tools added.
full security breakdown →-
analyze_dependencies -
benchmark_gate -
evaluate_app_builder_flow -
evaluate_batch -
evaluate_code -
evaluate_code_single_judge -
evaluate_code_streaming -
evaluate_diff -
evaluate_file -
evaluate_focused -
evaluate_git_diff -
evaluate_policy_aware -
evaluate_project -
evaluate_public_repo_report -
evaluate_then_fix -
evaluate_with_progress -
explain_finding -
fix_code -
get_finding_stats -
get_judges
No releases yet.
No releases yet.