What it does
Draugr provides security scanning for AI agents through the Model Context Protocol. According to its publisher, it covers static application security testing (SAST), software composition analysis (SCA), secrets detection, infrastructure as code (IaC) checks and dynamic application security testing (DAST), with findings ranked by real risk.
It suits teams that want an agent to run security checks on code, dependencies, configuration or running applications as part of its work, and that want the results ordered by severity rather than as a flat list.
The source gives no detail on setup, supported languages or how scans are launched, so those points are not covered here. Its repository is hosted on GitHub.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 17 Nov 2026 · its page on the source
Draugr
Security scanning for AI agents: SAST, SCA, secrets, IaC, DAST, ranked by real risk.
v0.182.0As shown on registry.modelcontextprotocol.io when we last read it