Generate and preview a single dataset entry for a specific scenario. Useful for quality inspection before generating the full dataset.
AI agents call preview_entry to retrieve information from OffensiveSET without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays data (a preview of a generated dataset entry) without creating, modifying, deleting, executing code, moving money, or triggering external operations. The most severe action is generating/querying data for display purposes, which falls squarely in the Read category.
From the tool's definition Tool generates and previews a single dataset entry for quality inspection before generating the full dataset. The verb "preview" and the stated purpose of inspection indicate read-only retrieval of generated content with no side effects or data modification.
Documented attack patterns abuse exactly the kind of access preview_entry gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OffensiveSET, and nothing reaches the server without passing your rules. This is the rule we recommend for preview_entry:
{
"version": "1",
"default": "deny",
"tools": {
"preview_entry": {}
}
}preview_entry is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Generate and preview a single dataset entry for a specific scenario. Useful for quality inspection before generating the full dataset. It is categorised as a Read tool in the OffensiveSET MCP Server, which means it retrieves data without modifying state.
Register the OffensiveSET MCP server in PolicyLayer and add a rule for preview_entry: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches OffensiveSET. Nothing to install.
preview_entry is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the preview_entry rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for preview_entry. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
preview_entry is provided by the OffensiveSET MCP server (pentesterflow/offensiveset). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 10 OffensiveSET tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
10 OffensiveSET tools catalogued and risk-classified — across an index of 42,500+ MCP servers.