Skip to content

agent security scanner mcp for Grok

io.github.sinewaveai/agent-security-scanner-mcp

Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.

client:Grok transport:stdio runtime:npm

Install agent security scanner mcp in Grok

.mcp.json (in your project root)

{
  "mcpServers": {
    "agent-security-scanner-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "agent-security-scanner-mcp"
      ]
    }
  }
}

Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs

agent security scanner mcp in other clients