Agentshield
🛡️ The security firewall for AI agent tools & MCP servers (Claude, GPT-5.6, Gemini 3.7, Antigravity, Cursor, Codex, Hermes). Catch command injection, secret theft & toxic flows in <50ms. 100% offline Rust SAST + 1-click auto-fix + SARIF.
AST Security Audit & Verification Scorecard98% Score
Last verified & scanned on: Aug 20, 2026
5-Pillar Verification Breakdown (100-Point Standard)
Total Score: 98 / 100 ptsSandboxed edge isolate runtime safety verified.
Model Context Protocol tool alignment verified.
License verified as Other.
Documentation and usage guides inspected.
Active Git provenance verified.
How to Improve This Score to 100/100
To increase this repository's score from 98% to 100%, author and contributors can apply these updates to GitHub:
- +2 pts:Edge Sandbox Safety — Ensure code avoids dynamic eval(), unsanitized child_process spawns, and hardcoded secrets.
Universal Client Configurations & Quickstart
Select your environment below for instant 1-click CLI installer or verified JSON client configs
# 1-Click install into Claude Desktop (auto-injects into claude_desktop_config.json):
npx unofficialos add agentshield
# 1-Click install into Cursor IDE (.cursor/mcp.json):
npx unofficialos add agentshield --client cursor
# Or run directly via terminal:
npx -y github:aiconnai/agentshieldMore MCP Servers Tools
View allOfficial ConnectMeGuru travel eSIM & AI agent toolkit with 14 live zero-config tools for catalog search, balance checks, and instant eSIM provisioning.
Model Context Protocol Servers
The official Python SDK for Model Context Protocol servers and clients