git clone https://github.com/your-repo/code-audit-fp-filter.git
cd code-audit-fp-filter

pip install -r requirements.txt

cp config.json.example config.json

python main.py --transport stdio

python main.py --transport sse --port 8000

{
  "mcpServers": {
    "code-audit-fp": {
      "command": "python",
      "args": ["/path/to/code-audit-fp-filter/main.py", "--transport", "stdio"],
      "env": {
        "CONFIG_PATH": "/path/to/config.json"
      }
    }
  }
}

# 通过MCP客户端调用
result = await mcp_client.call_tool(
    "filter_false_positives",
    scan_results=[
        {
            "tool": "semgrep",
            "rule_id": "python.lang.security.injection.sql-injection",
            "file": "app/database.py",
            "line": 42,
            "code": "cursor.execute(user_input)",
            "severity": "ERROR",
            "message": "SQL injection vulnerability"
        }
    ],
    source_code_dir="/path/to/project",
    filter_level="all",
    confidence_threshold=0.7
)

result = await mcp_client.call_tool(
    "analyze_code_context",
    file_path="app/database.py",
    line_number=42,
    context_lines=10,
    check_types=["dead_code", "security_guards", "input_validation"]
)

result = await mcp_client.call_tool(
    "train_false_positive_model",
    training_data=[
        {
            "features": {
                "rule_confidence": 0.8,
                "severity_score": 1.0,
                "code_complexity": 0.6,
                "data_flow_length": 5,
                "has_security_guards": 0.0,
                "has_input_validation": 0.0,
                "is_test_code": 0.0,
                "file_depth": 3,
                "line_count": 1
            },
            "is_false_positive": False
        }
    ],
    model_type="random_forest",
    validation_split=0.2
)

{
  "rule_filter": {
    "enabled": true,
    "global_whitelist": [
      {
        "file_pattern": "*/test/*",
        "reason": "测试代码",
        "confidence": 0.9
      }
    ],
    "global_blacklist": [
      {
        "file_pattern": "*/production/*",
        "reason": "生产环境代码",
        "confidence": 0.9
      }
    ]
  }
}

{
  "context_filter": {
    "enabled": true,
    "security_guard_keywords": ["sanitize", "escape", "validate"],
    "input_validation_keywords": ["isinstance", "len", "range"],
    "false_positive_threshold": 0.5
  }
}

{
  "ml_filter": {
    "enabled": true,
    "model_path": "models/false_positive_model.pkl",
    "onnx_model_path": "models/false_positive_model.onnx",
    "confidence_threshold": 0.7
  }
}

code-audit-false-positive-filter/
├── code_audit_fp/
│   ├── __init__.py
│   ├── server.py          # MCP服务器实现
│   ├── models.py          # 数据模型
│   └── filters/
│       ├── __init__.py
│       ├── base.py        # 过滤器基类
│       ├── rule_filter.py # L1规则过滤器
│       ├── context_filter.py # L2上下文过滤器
│       └── ml_filter.py   # L3 ML过滤器
├── main.py                # 入口点
├── requirements.txt       # 依赖
├── config.json            # 配置文件
└── README.md              # 说明文档

from code_audit_fp.filters import MLFilter

ml_filter = MLFilter(config)
result = await ml_filter.train_model(
    training_data=your_training_data,
    model_type="random_forest",
    validation_split=0.2
)