mcp-redflag

eldoctorams/mcp-redflag

★ 0 stars Unknown language Security Updated 5d ago

Adversarial security benchmark and red-team lab for MCP servers and Agent Skills — reproducible tests, evidence reports and CI-ready scoring.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "mcp-redflag": {
      "command": "npx",
      "args": [
        "-y",
        "eldoctorams/mcp-redflag"
      ]
    }
  }
}

README Excerpt

> A reproducible red-team benchmark for MCP servers and Agent Skills. MCP RedFlag is being designed as an adversarial lab—not merely another static scanner. It will measure how agent systems behave when tools, manifests, resources and supply-chain components become hostile, then produce evidence-backed, CI-friendly findings.

mcp-redflag

Quick Install

README Excerpt

Related Security Servers