Skip to content
Grok

injectshield for Grok

io.github.bch1212/injectshield

Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.

client:Grok transport:stdio runtime:npm

Install injectshield in Grok

.mcp.json (in your project root)

Held in this page only — never stored, logged, or sent anywhere but back to your screen.

{
  "mcpServers": {
    "injectshield": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@injectshield/mcp"
      ],
      "env": {
        "INJECTSHIELD_API_KEY": "<INJECTSHIELD_API_KEY>",
        "INJECTSHIELD_API_BASE": "<INJECTSHIELD_API_BASE>"
      }
    }
  }
}

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

injectshield in other clients