MCP server with specialized judges to evaluate AI-generated code for security, cost, scalability, cloud readiness, and best practices.
This repository also configures its own agents. See what judges tells them →
Agent Claude Code
Detects misuse patterns unique to popular frameworks: React hook violations, Express middleware ordering, Next.js SSR data leaks, Angular DomSanitizer bypass, Vue v-html XSS, Django settings & template safety, Spring Boot security configuration, ASP.NET Core authorization & CORS, Flask SSTI, FastAPI auth dependencies…
Agent Claude Code
Detects APIs, imports, methods, and patterns that are commonly hallucinated by AI code generators — non-existent standard library functions, fabricated package names, phantom methods, and incorrect API signatures that look plausible but don't exist.
Agent Claude Code
Evaluates Terraform, Bicep, and ARM templates for security misconfigurations, hardcoded secrets, missing encryption, overly permissive network/IAM rules, and IaC best-practice violations.
Agent Claude Code
Detects mismatches between stated intent (comments, docstrings, function names) and actual implementation — stubs, TODO-only bodies, misleading names, and empty implementations that AI code generators commonly produce.
Agent Claude Code
Evaluates code for hardcoded strings, date/number formatting, RTL support, locale-aware sorting, Unicode handling, and translation-ready patterns.
Agent Claude Code
Evaluates code for PII in log output, sensitive data redaction, appropriate log levels, and compliance with data protection requirements in logging.
Agent Claude Code
Detects logic errors common in AI-generated code: inverted conditions, off-by-one errors, dead code branches, function name/implementation mismatches, and incomplete control flow.
Agent Claude Code
Evaluates code for readability, modularity, complexity, naming conventions, and technical debt indicators that affect long-term maintenance costs.
Agent Claude Code
Detects stylistic fingerprints characteristic of specific AI code generators (ChatGPT/GPT-4, Claude, Copilot, Gemini) to flag code that may carry model-specific biases, hallucinations, or blind spots.
Agent Claude Code
Detects self-contradicting patterns: duplicate function definitions, contradictory boolean assignments, dead code after returns, conflicting configs, and TODO density.
Agent Claude Code
Evaluates code for structured logging, distributed tracing (OpenTelemetry), metrics exposition, alerting hooks, correlation IDs, and dashboarding readiness.
Agent Claude Code
Detects unnecessary abstractions, premature generalisation, wrapper-mania, and design-pattern misuse. Especially relevant for AI-generated code which tends toward over-abstraction.
Agent Claude Code
Evaluates code for memory allocation efficiency, GC pressure, lazy loading, bundle size, render performance, database query optimization, and runtime hot spots.
Agent Claude Code
Evaluates code for OS/platform independence, vendor lock-in avoidance, cross-environment compatibility, and abstraction of platform-specific functionality.
Agent Claude Code
Evaluates code for API rate limiting, request throttling, backoff strategies, quota management, and protection against abuse and resource exhaustion.
Agent Claude Code
Evaluates code for error recovery, retry logic, circuit breakers, graceful degradation, idempotency, dead letter queues, chaos readiness, and fault tolerance.
Agent Claude Code
Evaluates code for its ability to handle growth — horizontal/vertical scaling readiness, statelessness, concurrency, bottlenecks, and performance under load.
Agent Claude Code
Holistic security assessment covering insecure data flows, weak cryptography, missing security controls, unsafe deserialization, XML external entities, prototype pollution, and other broad vulnerability patterns across all supported languages.
Agent Claude Code
Evaluates code quality, maintainability, testing practices, documentation, SOLID principles, design patterns, error handling, and secure software development lifecycle (SSDLC) compliance.
Agent Claude Code
Evaluates code for test-to-code ratio, test isolation, mocking strategy, edge case coverage, flaky test patterns, and test pyramid balance (unit/integration/e2e).
Agent Claude Code
Evaluates code for user experience patterns including loading states, error feedback, responsive design, mobile-friendliness, and interaction quality.
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: