MCP Code Sanitizer is an AI-powered code review and analysis server that integrates with Claude, Cursor, VS Code, and GitHub Actions to find bugs, vulnerabilities, and security issues in your code.

• analyze_code — Strictly review a code fragment for bugs, security vulnerabilities, and code quality issues, returning a score (0–100) with categorized issues, warnings, and suggestions.

• compare_code — Compare two versions of code to detect regressions, improvements, or neutral changes, with a merge/request_changes recommendation.

• explain_code — Generate a step-by-step explanation of code, tailored to a junior, middle, or senior audience.

• generate_tests — Automatically create unit tests (pytest, jest, go test, etc.) covering happy paths, edge cases, and security scenarios.

• analyze_file — Analyze an entire file from disk, with automatic language detection by extension and parallel chunking for large files.

• generate_report — Convert any analysis result into a formatted HTML report, optionally saved to a specified path.

• cache_info — View cache statistics (hit rate, entry count, etc.) or clear the cache entirely.

Generates Jest test cases with happy path, edge cases, and security tests.

Generates pytest test cases with happy path, edge cases, and security tests.

Claude / Cursor / VS Code ──MCP──► code-sanitizer ──REST──► Groq API
 (server.py) (llama-3.3-70b)

{
 "summary": "Critical SQL injection and secret exposed in logs",
 "score": 23,
 "issues": [
 {
 "severity": "critical",
 "line": 2,
 "title": "SQL Injection",
 "description": "f-string directly interpolates user_id into query",
 "fix": "cursor.execute('SELECT * FROM users WHERE id = %s', (user_id,))"
 }
 ],
 "warnings": [{"title": "No exception handling", "description": "..."}],
 "suggestions": ["Consider using an ORM instead of raw SQL"]
}

claude mcp add code-sanitizer -e GROQ_API_KEY=gsk_your_key -- uvx mcp-code-sanitizer

{
 "mcpServers": {
 "code-sanitizer": {
 "command": "uvx",
 "args": ["mcp-code-sanitizer"],
 "env": {
 "GROQ_API_KEY": "gsk_your_key_here"
 }
 }
 }
}

{
 "mcpServers": {
 "code-sanitizer": {
 "command": "uvx",
 "args": ["mcp-code-sanitizer"],
 "env": {
 "GROQ_API_KEY": "gsk_your_key_here"
 }
 }
 }
}

{
 "servers": {
 "code-sanitizer": {
 "command": "uvx",
 "args": ["mcp-code-sanitizer"],
 "env": {
 "GROQ_API_KEY": "gsk_your_key_here"
 }
 }
 }
}

git clone https://github.com/notasandy/mcp-code-sanitizer
cd mcp-code-sanitizer
pip install -r requirements.txt
cp .env.example .env # add your GROQ_API_KEY
python server.py

{
 "command": "python",
 "args": ["/full/path/to/server.py"],
 "env": { "GROQ_API_KEY": "gsk_your_key_here" }
}

# .github/workflows/ai-review.yml
name: AI Code Review
on:
 pull_request:
 types: [opened, synchronize]

permissions:
 contents: read
 pull-requests: write

jobs:
 review:
 runs-on: ubuntu-latest
 steps:
 - uses: notasandy/mcp-code-sanitizer@v1
 with:
 groq_api_key: ${{ secrets.GROQ_API_KEY }}

Review this code for vulnerabilities:

def get_user(user_id):
 query = f"SELECT * FROM users WHERE id = {user_id}"
 return db.execute(query)

analyze_file /path/to/my_script.py
generate_tests for this function: ...
compare_code — before vs after refactor, did it get better?
generate_report and save to /tmp/report.html

mcp-code-sanitizer/
├── server.py # FastMCP entry point
├── config.py # Constants — keys, limits, extension map
├── groq_client.py # Async Groq client with auto-retry on 429
├── cache.py # In-memory LRU cache with TTL
├── prompts.py # System prompts for all tools
└── tools/
 ├── analyze.py # analyze_code
 ├── compare.py # compare_code
 ├── explain.py # explain_code
 ├── tests.py # generate_tests
 ├── file_tool.py # analyze_file — chunking + parallel analysis
 ├── cache_tool.py # cache_info
 └── report.py # generate_report — HTML output