AgentShield Enterprise Zero-Leak Secret Defense & Kernel Sandbox
● Activeio.github.RitualDev-Lab/agentshield
Enterprise Zero-Leak Secret Defense & Kernel Sandbox for Autonomous AI Agents
Connect this server
One click to install, or copy the config below. Suits: Claude Desktop · Cursor.
Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):
{
"mcpServers": {
"agentshield": {
"command": "npx",
"args": [
"-y",
"@ritualdev-lab/agentshield@0.2.2"
]
}
}
}claude mcp add agentshield -- npx -y @ritualdev-lab/agentshield@0.2.2codex mcp add agentshield -- npx -y @ritualdev-lab/agentshield@0.2.2code --add-mcp '{"name":"agentshield","type":"stdio","command":"npx","args":["-y","@ritualdev-lab/agentshield@0.2.2"]}'Syntax from each client's docs (Claude Code: claude mcp add; Codex: codex mcp add; VS Code: code --add-mcp). Placeholders in angle brackets are values you fill in.
A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.
- Category
- Security & Identity
- Version
- 0.2.2
- Registry
- active
- Published
- 11/19/2026
Is it safe? Is it maintained?
Serverdex check: Nov 22, 2026Looks healthy: AgentShield Enterprise Zero-Leak Secret Defense & Kernel Sandbox is maintained, open source.
- Maintained
- Active
- Last commit 2 days ago (Nov 19, 2026), 6 open issues.
- Official registry
- Active
- Published as io.github.RitualDev-Lab/agentshield in the official MCP registry, version 0.2.2.
- Source
- Open source, Apache-2.0
- Public repository under the Apache-2.0 licence, 5 stars, 5 forks.
- Runs
- On your machine
- A local npm package started by your client; it can reach whatever your user account can.
- Credentials
- None declared
- The registry entry declares no required environment variables.
- Owner
- Unclaimed
- Nobody has claimed this page yet; the data above comes from the registry, GitHub and the live check.
Facts only: last commit and licence from GitHub, the entry's status from the official registry, credentials from the live check. Not a code audit — run the security scan on the endpoint yourself.
On GitHub
read Nov 21, 2026- Stars
- 5
- Forks
- 5
- Last push
- Nov 19, 2026
- License
- Apache-2.0
TypeScriptagentic-aiai-agentsai-securitydata-loss-preventiondlpfirewalllangchainllamaindexllm-securitymcp-securitymodel-context-protocolowasp-top-10-llmprompt-injectionruntime-securityzero-trust
From the README
AgentShield Stop Claude Code, Cursor, Windsurf, and autonomous coding agents from leaking .env secrets, SSH keys, or running destructive shell commands. Zero runtime dependencies. 100% local & air-gapped by default. Recorded with Charm VHS from assets/demo.tape. Why this exists Autonomous coding agents have direct access to your shell, filesystem, and git repo. Even well-behaved agents routinely run cat .env, printenv, node -e 'console.log(process.env)', or commit live test keys into PRs—leaking raw credentials into third-party model APIs and git history. AgentShield intercepts commands and stdout/stderr before credentials leave your machine: • Obfuscation-resistant command firewall: Catches cat .e""nv, cat .e?v, /proc/self/environ, base64/xxd, tar/cp, and inline node/python env dumps. • Boundary-safe streaming redactor: Catches secrets split across arbitrary 1-byte TCP/stdio chunks and multiline PEM blocks (0 runtime dependencies, linear-time regex + Shannon entropy). • OS sandbox preflight & profiles: Generates and verifies macOS Seatbelt (sandbox-exec), Linux bwrap/Landlock, and Windows AppContainer isolation via agentshield doctor. • Unified 3-layer stack: Boot AgentShield + DBShield + SkillPrism from a single declarative ritual.policy.yaml via agentshield up. Try to break it (Contributors Wanted) Think you can bypass our .env / /proc/self/environ blocker or split a secret across stream chunks without triggering redaction?…
Read the full README on GitHub →Alternatives to AgentShield Enterprise Zero-Leak Secret Defense & Kernel Sandbox
All AgentShield Enterprise Zero-Leak Secret Defense & Kernel Sandbox alternatives →Best Security & Identity servers →The most-starred Security & Identity servers in the index, with their live-check result.
| Server | Stars | Last push | Live check |
|---|---|---|---|
| Handsy AI | 5,215 | Nov 2026 | Local / not checked |
| HOL Guard | 1,118 | Nov 2026 | Local / not checked |
| SonarQube MCP Server | 689 | Nov 2026 | Local / not checked |
| MCP Ssh Manager | 545 | Nov 2026 | Local / not checked |
| Security Detections | 529 | Nov 2026 | Local / not checked |
AgentShield Enterprise Zero-Leak Secret Defense & Kernel Sandbox: questions people ask
- Is AgentShield Enterprise Zero-Leak Secret Defense & Kernel Sandbox a remote or a local MCP server?
- According to its entry in the official MCP registry, AgentShield Enterprise Zero-Leak Secret Defense & Kernel Sandbox ships as a local package (npm) that your client starts on your machine.
- Is AgentShield Enterprise Zero-Leak Secret Defense & Kernel Sandbox safe to use?
- Looks healthy: AgentShield Enterprise Zero-Leak Secret Defense & Kernel Sandbox is maintained, open source. In detail — maintained: Active; official registry: Active; source: Open source, Apache-2.0; runs: On your machine; credentials: None declared. Serverdex check of Nov 22, 2026. This is a reading of the repository, the registry entry and the live check, not a code audit; run the Serverdex security scan on the endpoint before trusting it with real data.
- Is AgentShield Enterprise Zero-Leak Secret Defense & Kernel Sandbox still maintained?
- Active: the repository's last commit 2 days ago. Last push Nov 19, 2026, 5 GitHub stars, Apache-2.0 licence. Read from GitHub on Nov 21, 2026.
- How do I add AgentShield Enterprise Zero-Leak Secret Defense & Kernel Sandbox to Claude, Cursor or VS Code?
- Copy the config in "Connect this server" into your client's MCP config file (claude_desktop_config.json, ~/.cursor/mcp.json or .vscode/mcp.json), or use the one-click Add to Cursor / Add to VS Code buttons and the one-line commands for Claude Code and Codex; then restart the client.
More from RitualDev-Lab
All 9 servers by RitualDev-Lab →- DevShelf Developer Directory & Tool Discovery MCP ServerDiscover 570+ developer tools, free APIs, AI agents, and open-source libraries.Developer Tools★ 14
- SkillPrism MCP Context Optimizer & Tool Search ProxyProgressive Skill Disclosure, Semantic Tool Search & Context Optimizer for AI AgentsSearch & Web★ 3
- MCPShelf Model Context Protocol Registry, Search & Security AuditorDiscover, audit trust scores, and 1-click install 400+ verified MCP servers for AI coding agents.Security & Identity★ 1
- DBShield Database Guardrail & Sandboxing MCP ServerSafety-first Database Guardrail & Sandboxing MCP Server for AI Coding AgentsSecurity & Identity★ 1
More Security & Identity servers
Browse all Security & Identity →DBShield Database Guardrail & Sandboxing MCP Server
RitualDev-Lab
Safety-first Database Guardrail & Sandboxing MCP Server for AI Coding Agents
MCPShelf Model Context Protocol Registry, Search & Security Auditor
RitualDev-Lab
Discover, audit trust scores, and 1-click install 400+ verified MCP servers for AI coding agents.
WebSecAuditor AI Cybersecurity & Vulnerability Auditor
RitualDev-Lab
Enterprise-grade AI vulnerability auditor for web applications, APIs, and codebases.
OSINT MCP
rjn32s
26 free OSINT tools as MCP tools for AI agents. Auto-installs everything on first run.
OSINT
robyroro
Domain and website investigations: batch recon, shared infrastructure, CT history and public lookups
GrindFree Agent Security
ronin93
Pay-per-call agent security (x402): injection, tools, shell/SQL, memory, leaks, docs, safe reads
Add the badge to your site
Show visitors that AgentShield Enterprise Zero-Leak Secret Defense & Kernel Sandbox is listed here — it’s also the link we check for a free listing.
HTML — for your website
<a href="https://serverdex.io/server/io-github-ritualdev-lab-agentshield?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="AgentShield Enterprise Zero-Leak Secret Defense & Kernel Sandbox — listed on Serverdex" width="123" height="40" loading="lazy"></a>Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.
Markdown — for your README
[](https://serverdex.io/server/io-github-ritualdev-lab-agentshield?utm_source=badge)Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.
Install buttons — for your README
[](https://serverdex.io/install/cursor/io-github-ritualdev-lab-agentshield) [](https://serverdex.io/install/vscode/io-github-ritualdev-lab-agentshield) [](https://serverdex.io/install/claude-code/io-github-ritualdev-lab-agentshield)One click opens Cursor or VS Code with this server's config prefilled; the Claude Code button lands on the one-line command. The links point at Serverdex, so when your config changes the buttons keep working.
Install buttons — HTML for your docs
<a href="https://serverdex.io/install/cursor/io-github-ritualdev-lab-agentshield"><img src="https://serverdex.io/brand/install-cursor.svg" alt="Add to Cursor — via Serverdex" width="140" height="28"></a>
<a href="https://serverdex.io/install/vscode/io-github-ritualdev-lab-agentshield"><img src="https://serverdex.io/brand/install-vscode.svg" alt="Add to VS Code — via Serverdex" width="147" height="28"></a>
<a href="https://serverdex.io/install/claude-code/io-github-ritualdev-lab-agentshield"><img src="https://serverdex.io/brand/install-claude-code.svg" alt="Open in Claude Code — via Serverdex" width="180" height="28"></a>Same buttons as plain links for a docs page or website.
Prefer a live badge with the score, stars and live check? Score badge (links to a page that explains the number and back to this listing).