io.github.bch1212/injectshield

io.github.bch1212/injectshield·v0.1.4·AI & LLMs

Quality Score

/100

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

Repository →Website →

§01 Install

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "injectshield": {
      "command": "npx",
      "args": [
        "-y",
        "@injectshield/mcp"
      ],
      "env": {
        "INJECTSHIELD_API_KEY": "<your-injectshield_api_key>",
        "INJECTSHIELD_API_BASE": "https://api.injectshield.dev"
      }
    }
  }
}

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "injectshield": {
      "command": "npx",
      "args": [
        "-y",
        "@injectshield/mcp"
      ],
      "env": {
        "INJECTSHIELD_API_KEY": "<your-injectshield_api_key>",
        "INJECTSHIELD_API_BASE": "https://api.injectshield.dev"
      }
    }
  }
}

Cline (cline_mcp_settings.json)