by affaan-m · MCP 服务器 · ★ 1.3k
AgentShield Security auditor for AI agent configurations Scans Claude Code setups for hardcoded secrets, permission misconfigs, hook injection, MCP server risks, and agent prompt injection vectors. []() []() Quick Start · What It Catches · Opus Pipeline · GitHub Action · MiniClaw · Distribution · Changelog Why The AI agent ecosystem is growing faster than its security tooling.
| Stars | 1,295 |
| Forks | 287 |
| Language | TypeScript |
| Category | MCP 服务器 |
| License | MIT |
| Quality Score | 74.6449911771814/100 |
| Open Issues | 20 |
| Last Updated | 2026-10-18 |
| Created | 2026-02-11 |
| Platforms | claude-code, cli, mcp, node |
| Est. Tokens | ~18k |
Explore other popular mcp 服务器 tools:
agentshield is AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️. It is categorized as a MCP 服务器 with 1.3k GitHub stars.
agentshield is primarily written in TypeScript. It covers topics such as ai-agent, anthropic, claude-code.
You can find installation instructions and usage details in the agentshield GitHub repository at github.com/affaan-m/agentshield. The project has 1.3k stars and 287 forks, indicating an active community.
agentshield is released under the MIT license, making it free to use and modify according to the license terms.