Code Sentinel

A pattern-based code analyzer that catches the subtle issues AI assistants tend to introduce: empty catch blocks that swallow errors, fake implementations that always return true, TODO placeholders left behind, and hardcoded secrets. Exposes five tools through MCP: analyze_code for full JSON output, generate_report for visual HTML summaries, and three focused checkers for security, deceptive patterns, and placeholders. Scans for 93 distinct patterns across TypeScript, Python, Go, Rust, Java, and JavaScript. Works locally via stdio or as a remote Cloudflare Workers endpoint. Unlike AST-based linters that validate syntax, this specifically hunts for semantically valid code that hides failures or creates false confidence. Useful when reviewing AI-generated code before it ships or when you want to audit error handling patterns across a codebase.