The safeguards map / 3.7 Admission and owner settings
DefenseClaw
Drafted with AI
Drafted with AI from the cited sources under the direction of UnGovr staff. UnGovr holds editorial responsibility for this page. How this site is made
An open-source operator tool that scans skills, Model Context Protocol (MCP) servers and plugins before they run and blocks or quarantines them by severity or by an owner's allow and block lists.
Where it sits
3.7 Admission and owner settings (primary): Checks a skill, MCP server or plugin when it appears or is installed, and blocks, quarantines, warns or allows it from the scan severity and the owner's block and allow lists.
Admission is the check DefenseClaw runs when a skill, an MCP server or a plugin appears in a watched root, or when you install one with the CLI.
captured
A name you deny is blocked without a scan. A name you allow skips the scan.
captured
The admission block sets what each scan finding does, and asset_policy holds the only block and allow lists.
captured
Facts
- Concern
- security
- Names the law
- no
- Subject
- agentAI system
- Used by
- those who run it
- Runs
- at runtime
- Policy comes from
- owner-entered settings
Handoffs
produces Runtime records: OTLP
Every quote is verbatim from a stored capture of the page linked under it. Placement is our reading of the product's own documentation; no publisher has reviewed or endorsed it. Rows CC BY 4.0. Names, marks and logos belong to their owners; logos identify each product and are not part of the dataset.