📡 MCP Radar

RitualDev-Lab/AgentShield

Enterprise-Grade Zero-Leak Secret Defense & Sandbox for Autonomous AI Coding Agents (Claude Code, Cursor, Windsurf, Codex, Antigravity)

⭐ 3 stars
⑂ 5 forks
TypeScript
momentum ▲ 20.0
created 2026-10-12
on radar since 2026-10-15
agentic-aiaiai-skillai-skillsmcpmcp-clientmcp-servermcp-serversmcp-tools
View on GitHub ↗Homepage ↗

About AgentShield

Zero-Leak Secret Defense & Shell Sandbox for Autonomous AI Coding Agents

⚡ Quick Start • 📖 Full Guide • 🛡️ Agent Sandbox • 🐙 GitHub Action • 🤖 Agent Skill • 📋 Compliance • 🏆 Bounties • 🏛️ Governance • 📜 Grants • 👥 Contributors • 💖 Sponsor (Dodo) • 🌐 Website

Autonomous coding agents (Claude Code, Cursor, Windsurf, Codex, Antigravity) are routinely granted terminal and file access to inspect codebases and resolve bugs. Without a guardrail, agents frequently:

Vulnerability Vector Real-World Agent Behavior Threat Impact :--- :--- :--- Context Window Leak Agent runs cat .env or type .env to read configs. Production credentials leak to third-party model inference APIs & chat history. Accidental Exfiltration Agent runs curl or shell scripts with exported tokens. Ephemeral tokens dumped into terminal logs & CI artifacts. Git Contamination Agent writes tests or code with live test credentials. Secrets committed permanently into Git history and pull requests.

AgentShield acts as a deterministic, local-first zero-leak defense layer that intercepts, audits, and redacts credentials before they ever escape your machine.

No account or complicated daemon required. Run instantly with npx:

🛡️ 1. Autonomous Agent Shell Sandbox Intercept and sandbox agent terminal execution. If an agent tries to read .env, dump shell variables (printenv), or send keys to outbound endpoints, AgentShield blocks it on the fly:

From the project README.

Maintaining this server?

Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:

[![On MCP Radar](https://mcp.liqiwa.com/badge.svg)](https://mcp.liqiwa.com/s/RitualDev-Lab--AgentShield.html)

Related MCP servers

mkpoli/gmail-mcp

Multi-account Gmail MCP server on Cloudflare Workers — one deployment, one Google sign-in per connection, any MCP client

⭐ 5TypeScript
priyansh-narang2308/TheBlacklisted-NitroStack

Protocol-0 is an MCP (Model Context Protocol) server that gives AI assistants, Claude, Cursor, ChatGPT, NitroChat, or any MCP-compatible client, real authority to act as your Site Reliability Engineer

⭐ 4TypeScript
s3hq4y/portal

Portal VS Code extension - public MCP endpoint

⭐ 4TypeScript
rynald0cst0ltziam/Warden-AI

The structurally-verified context layer for AI coding agents. Cut 50-90% of your agent's token spend.

⭐ 3TypeScript
FrancisTCE/gresui-web

simple postgres ui + mcp service layer. NPM: https://www.npmjs.com/package/gresui-web

⭐ 3TypeScript
RitualDev-Lab/SkillPrism

Progressive Skill Disclosure & Context Compaction Engine for Autonomous AI Coding Agents. Reduces prompt token bloat by 96.7% using JIT discovery, ephemeral schema injection, and semantic receipts.

⭐ 3TypeScript

📬 Get the weekly radar in your inbox

The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.