Draugr is a Model Context Protocol (MCP) server: Security scanning for AI agents: SAST, SCA, secrets, IaC, DAST, ranked by real risk. In practice that means any MCP-compatible AI assistant can call Draugr's tools directly — the model decides when to use them in a conversation or agent run.
No credentials are required — it works out of the box. The current release is v0.111.1, published under the Apache-2.0 license, with source at draugr-dev/draugr on GitHub.
Draugr is listed under Version Control on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Draugr for draugr.dev, claim this listing to verify ownership, earn the Verified badge, and keep the details current.
