OffensiveSET
未认领Offensive Security Dataset Generator — MCP server for generating high-quality pentesting conversation datasets for LLM fine-tuning
安装
$
claude mcp add offensiveset node $(pwd)/dist/index.js工具（10 个）
export_for_training
Convert to Qwen ChatML, ShareGPT, OpenAI, or Alpaca format
generate_dataset
V1 generator — baseline pentesting conversations
generate_dataset_v2
V2 generator — dynamic outputs, failures, deep thinking (recommended)
get_dataset_stats
Analyze a generated dataset
list_scenarios
Browse 45 attack scenarios with filtering
list_tools
Display 40 pentesting tools and capabilities
merge_datasets
Combine multiple datasets with deduplication
preview_entry
Preview a single entry before full generation
quality_score
Deep quality analysis with A-F grading
validate_dataset
Check JSONL structure, schema compliance, placeholder detection