by jnMetaCode · MCP Server · ★ 112
ShellWard 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.
| Stars | 112 |
| Forks | 19 |
| Language | TypeScript |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 72.6261568442478/100 |
| Open Issues | 5 |
| Last Updated | 2026-06-23 |
| Created | 2026-03-12 |
| Platforms | claude-code, mcp, node |
| Est. Tokens | ~17k |
These tools work well together with shellward for enhanced workflows:
Explore other popular mcp server tools:
shellward is AI 应用合规网关 · 一行命令体检 AI 项目的「数据出境 / 硬编码密钥 / 个人信息暴露」(网安法·PIPL·等保2.0·数据出境·AI标识),并给出境内模型替代建议;可作运行时防护拦截注入与数据外泄 · 中文优先 · 零依赖 · 开源. It is categorized as a MCP Server with 112 GitHub stars.
shellward is primarily written in TypeScript. It covers topics such as agent-security, ai-agent, ai-firewall.
You can find installation instructions and usage details in the shellward GitHub repository at github.com/jnMetaCode/shellward. The project has 112 stars and 19 forks, indicating an active community.
shellward is released under the Apache-2.0 license, making it free to use and modify according to the license terms.