AgentShield MCP Server
mkarvan/AgentShield
[](https://agentrank-ai.com/tool/mkarvan--AgentShield/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) 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.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
mkarvan/AgentShield is a Python tool licensed under MIT. 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.
Ranked #22199 out of 24846 indexed tools.
Ecosystem
Score Breakdown
3 stars → early stage
Last commit 1mo ago → moderate activity
No issues filed → no history to score
0 contributors → solo project
No dependents → no downstream usage
17 weekly installs → early adoption
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
How to Improve
Matched Queries
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.