MCP Code Sanitizer
🔍 mcp-code-sanitizer
Строгий AI-ревьюер кода, который проверяет ваш код с помощью Groq LLM прямо из Claude Desktop, Cursor или любого другого MCP-совместимого агента.
Claude Desktop ──MCP──► code-sanitizer ──REST──► Groq API
(server.py) (llama-3.3-70b)✨ Возможности
Инструмент | Описание |
| Строгий ревью кода — ошибки, уязвимости, оценка 0–100 |
| Сравнивает две версии, находит регрессии, рекомендует слияние/запрос изменений |
| Пошаговое объяснение для уровня junior/middle/senior |
| Генерирует тесты pytest/jest/go с учетом основных сценариев, граничных случаев и проверок безопасности |
| Анализирует весь файл с диска с параллельным разбиением на части |
| Создает красивый HTML-отчет на основе любого результата анализа |
| Статистика кэша и его очистка |
Пример ответа
{
"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"]
}Related MCP server: Claude Code Review MCP
🚀 Быстрый старт
1. Клонируйте репозиторий
git clone https://github.com/YOUR_USERNAME/mcp-code-sanitizer
cd mcp-code-sanitizer2. Создайте виртуальное окружение и установите зависимости
python -m venv venv
# macOS / Linux
source venv/bin/activate
# Windows
venv\Scripts\activate
pip install -r requirements.txt3. Добавьте ваш API-ключ Groq
Получите бесплатный ключ на console.groq.com/keys
cp .env.example .env
# Open .env and set GROQ_API_KEY=gsk_...4. Протестируйте сервер
python server.pyТишина означает, что все работает — сервер ожидает MCP-запросы через stdio.
🔌 Подключение к Claude Desktop
Найдите файл конфигурации и добавьте секцию mcpServers:
ОС | Путь к конфигурации |
macOS |
|
Windows |
|
Linux |
|
{
"mcpServers": {
"code-sanitizer": {
"command": "/full/path/to/venv/bin/python",
"args": ["/full/path/to/server.py"],
"env": {
"GROQ_API_KEY": "gsk_your_key_here"
}
}
}
}Перезапустите Claude Desktop — вы увидите иконку 🔧 в чате.
🔌 Подключение к Cursor
Создайте .cursor/mcp.json в корне вашего проекта:
{
"mcpServers": {
"code-sanitizer": {
"command": "/full/path/to/venv/bin/python",
"args": ["/full/path/to/server.py"],
"env": {"GROQ_API_KEY": "gsk_your_key_here"}
}
}
}🧪 Тестирование через MCP Inspector
source venv/bin/activate # or venv\Scripts\activate on Windows
fastmcp dev inspector server.pyОткроется браузерный интерфейс с полным набором инструментов для тестирования.
💬 Использование в чате
После подключения к Claude Desktop просто напишите:
Review this code for vulnerabilities:
def get_user(user_id):
query = f"SELECT * FROM users WHERE id = {user_id}"
return db.execute(query)Или явно вызовите инструмент:
Use analyze_file on /path/to/my_script.py
Generate tests for this function: ...
Compare these two versions and tell me if it got better: ...🏗️ Архитектура
mcp-code-sanitizer/
├── server.py # FastMCP entry point (39 lines)
├── config.py # Constants — keys, limits, mappings
├── groq_client.py # Groq API client with auto-retry on rate limits
├── cache.py # In-memory 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)⚙️ Конфигурация
Все настройки задаются через переменные окружения или .env:
Переменная | По умолчанию | Описание |
| — | Обязательно. Получите на console.groq.com |
|
| Модель Groq |
|
| Время жизни кэша в секундах |
|
| Максимальное количество записей в кэше |
Доступные модели Groq
Модель | Скорость | Качество |
| ⚡⚡ | ⭐⭐⭐⭐⭐ (по умолчанию) |
| ⚡⚡⚡ | ⭐⭐⭐ |
| ⚡⚡ | ⭐⭐⭐⭐ |
📦 Требования
fastmcp>=2.3.0
httpx>=0.27.0
python-dotenv>=1.0.0🤝 Участие в разработке
PR и Issues приветствуются! Особенно интересны:
Поддержка других LLM-провайдеров (OpenAI, Anthropic)
Новые инструменты (аудит безопасности, проверка зависимостей, анализ сложности)
Улучшения промптов
📄 Лицензия
MIT — делайте что хотите. Будем признательны за звезду на GitHub ⭐
🔗 Ссылки
Available Tools
7 toolsanalyze_codeC
Strict analysis of a code fragment using Groq LLM.
Inputs: code (required), language, context. Returns: result
analyze_fileA
Analyzes a whole code file from disk. Automatically detects language by file extension. Large files are split into chunks and analyzed in parallel.
Inputs: file_path (required), language, context. Returns: result
cache_infoA
Shows cache statistics or clears the cache Args: clear: True - clears the cache, False - shows statistics.
Returns: JSON with cache stats or clear result.
Inputs: clear. Returns: result
compare_codeA
Compares two versions of code and evaluates whether the change is an improvement.
Performs a structured diff analysis: identifies what improved, what regressed, and what changed neutrally. Returns a merge recommendation based on the findings. Useful for code review, refactoring validation, and AI-generated code verification.
Inputs: code_before (required), code_after (required), language, context. Returns: result
explain_codeA
Explains what code does - step by step and clearly. Args: code: Code to explain. language: Programming language. audience: Target audience level - junior, middle, or senior. Returns: JSON with step-by-step explanation, key concepts, and gotchas.
Inputs: code (required), language, audience. Returns: result
generate_reportA
Generates a beautiful HTML report from analyze_code or analyze_file results. Args: analysis_json: JSON string from analyze_code or analyze_file. output_path: Path to save the HTML file (optional). source_name: File/fragment name for the report title. Returns: JSON with fields: html, saved_to, length.
Inputs: analysis_json (required), output_path, source_name. Returns: result
generate_testsA
Generates tests for the provided code. Args: code: Code to generate tests for. language: Programming language. framework: Test framework (optional - pytest, jest, unittest, etc.). Returns: JSON with test cases, runnable test code, and coverage estimate.
Inputs: code (required), language, framework. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Each tool has a clearly distinct purpose: code fragment analysis, whole file analysis, cache management, code comparison, code explanation, report generation, and test generation. No overlap in functionality.
All tool names follow a consistent verb_noun pattern using snake_case (e.g., analyze_code, generate_tests). No inconsistencies in style.
7 tools is a well-scoped set for code analysis and sanitization tasks, covering the core operations without being overwhelming or too sparse.
The tool surface covers analysis, comparison, explanation, test generation, and reporting. A minor gap is the lack of code transformation or refactoring tools, but the set is reasonable for the stated domain.
Maintenance
Related MCP Connectors
AI code governance and code review for Claude Code, Copilot and Cursor. Checks rules and security.
AI-powered codebase analysis — call graphs, security, dead code, complexity. 150+ tools.
Checks AI-written code for leaked keys and made-up packages, on your machine. Never uploads code.
Scores your code across 12 areas, with findings, fix prompts, and re-assessment in your AI agent
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA server that enables interaction with PostgreSQL, MySQL, MariaDB, or SQLite databases through Claude Desktop using natural language queries.1-
- AlicenseAqualityDmaintenanceAn MCP server that provides code review functionality using OpenAI, Google, and Anthropic models, serving as a "second opinion" tool that works with any MCP client.134MIT
- AlicenseAqualityDmaintenanceEnables comprehensive security scanning of code projects, detecting vulnerabilities in dependencies, code patterns (XSS, eval, etc.), and exposed secrets, with detailed reports in Spanish prioritized by severity.4MIT
- AlicenseAqualityDmaintenanceAI-powered code review tool that detects AI-generated code defects invisible to traditional linters — hallucinated packages, deprecated APIs, cross-file contradictions, hidden security anti-patterns, and over-engineering. Works as a standalone CLI, GitHub Action, or MCP server. Supports TypeScript, Python, Java, Go, and Kotlin. Free for individuals, no API key required.441Business Source 1.1