The problem
AI-generated code is everywhere. GitHub Copilot, Claude, ChatGPT — they all write code fast. But they also introduce subtle bugs, SQL injections, and insecure patterns that look totally fine at first glance.
I wanted a tool that sits inside my AI agent and reviews code before I ship it. Not a linter. Not a static analyzer. A strict senior engineer who actually explains why something is wrong and shows the fix.
What I built
mcp-code-sanitizer — an MCP server that plugs into Claude Desktop or Cursor and gives you a strict AI code review powered by Groq's free API (llama-3.3-70b).
Claude Desktop ──MCP──► code-sanitizer ──REST──► Groq API
Enter fullscreen mode
Exit fullscreen mode
Tools available
Tool What it does
analyze_code Finds bugs, vulnerabilities, rates 0–100
compare_code Compares versions, detects regressions
explain_code Step-by-step explanation for any level
generate_tests Writes pytest/jest tests automatically
analyze_file Analyzes whole files with parallel…