AgentShield

active

Security layer for AI agents: real-time interception of pip/npm/cargo/gem/go installs via Hermes & OpenClaw plugins, Claude Code/Codex hooks, MCP, shell guard, PATH shim, execve, and index proxy. Checks CVEs (OSV/NVD/GitHub), typosquats, malware, licenses, provenance, trust, lockfile hashes. Offline mirror, hash-chained audit, SBOM/SARIF.

Code-only MCP server: no hosted endpoint, so you install and run it yourself. It is not probed, graded or counted in our reachability statistics.

Get it

Repository: github.com/mkarvan/AgentShield
License: MIT
Last update: 2026-09-22
GitHub stars: ★ 4

agent-security ai-agents claude-code cve llm-security mcp mcp-server npm package-security pip python sarif

Listed in

github · source

Run this server as a hosted endpoint? Submit the endpoint and it moves to the remote directory, where it is probed and graded.