MCP Directory
Back

shellward

by jnMetaCode · TypeScript · ★ 76

AI Agent Security Middleware — 8-layer defense, DLP data flow, prompt injection detection, zero dependencies. SDK + MCP server for Claude Code, Cursor, LangChain, Hermes Agent & more.

#agent-security#ai-agent#ai-firewall#ai-safety#ai-security#claude-code#cursor#data-exfiltration#dlp#guardrails#hermes-agent#langchain#llm-security#mcp#mcp-security#openclaw#pii-detection#prompt-injection#security#shellward

Install

npx -y github:jnMetaCode/shellward

Claude Desktop config

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "shellward": {
      "command": "npx",
      "args": [
        "-y",
        "github:jnMetaCode/shellward"
      ]
    }
  }
}

From the README

**AI Agent Security Middleware** — Protect AI agents from prompt injection, data exfiltration, and dangerous command execution. ShellWard acts as an LLM security middleware and AI agent firewall, intercepting tool calls at runtime to enforce agent guardrails before damage is done. 8-layer defense-in-depth, DLP-style data flow control, zero dependencies. Works as **standalone SDK** or **OpenClaw plugin**. [](https://www.npmjs.com/package/shellward) [](./LICENSE) [](#performance) [](#performance) [English](#demo) | [中文](#中文) > 7 real-world scenarios: server wipe → reverse shell → prompt inje…
Read full README on GitHub →

💡 Need a managed MCP host?

Try Claude Pro for the smoothest MCP experience, or browse our cloud-hosted servers.

Related ai & ml servers