// MCP TOOL REFERENCE

OFFENSIVESET TOOLS

10 tools from the OffensiveSET MCP Server, categorised by risk level.

View the OffensiveSET policy →
// ALL 10 OFFENSIVESET TOOLS
READ 6 tools
Read get_dataset_stats Get statistics about a previously generated dataset file. Read list_scenarios List all available pentesting scenario templates with categories, difficulties, and tags. Read list_tools List all pentesting tools defined in the dataset schema with their categories and capabilities. Read preview_entry Generate and preview a single dataset entry for a specific scenario. Useful for quality inspection before g... Read quality_score Deep quality analysis of a dataset. Scores entries on diversity, realism, complexity, and training readiness. Read validate_dataset Validate a PentesterFlow dataset for schema compliance, data quality, and training readiness.
WRITE 4 tools
Write export_for_training Convert a PentesterFlow dataset to a specific training format. Handles Qwen tool roles, thinking blocks, an... Write generate_dataset Generate an offensive security dataset for fine-tuning PentesterFlow model. Produces JSONL in ShareGPT/Chat... Write generate_dataset_v2 Generate an improved V2 offensive security dataset with unique outputs per entry, failure cases, deep think... Write merge_datasets Merge multiple PentesterFlow datasets into a single file with deduplication and balanced sampling.

Route OffensiveSET through PolicyLayer and every one of its 10 tools is checked against your policy before it runs.

GOVERN OFFENSIVESET →

Enforced before the call runs. Nothing to install.

// FAQ
How many tools does the OffensiveSET MCP server have? +

The OffensiveSET MCP server exposes 10 tools across 2 categories: Read, Write.

How do I enforce policies on OffensiveSET tools? +

Route the OffensiveSET server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard; they are enforced on every call before it reaches the server.

What risk categories do OffensiveSET tools fall into? +

OffensiveSET tools are categorised as Read (6), Write (4). Each category has a recommended default policy.

Enforce policy on every OffensiveSET tool call.

Deterministic rules across all 10 OffensiveSET tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

GOVERN OFFENSIVESET →

Free to start. No card required.

42,500+ MCP servers and 110,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.