merge_datasets

MCP tool from OffensiveSET by PentesterFlow

Combine multiple datasets with deduplication

How to use it

merge_datasets is exposed by the OffensiveSET MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the merge_datasets tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install OffensiveSET

$claude mcp add offensiveset node $(pwd)/dist/index.js

FULL OFFENSIVESET LISTING

Other tools in OffensiveSET (9)

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