promptguard

LLM security for AI coding agents -- protect applications from prompt injection, PII leakage, and data exfiltration. Works with Cursor, Claude Code, Codex, Copilot, Windsurf, and any MCP client.

Homepage Source

security llm prompt-injection ai-safety pii openai anthropic data-protection

Add to Cursor

This config will be passed to Cursor on install. Inspect `command`, `args`, and `env` before continuing.

{
  "command": "promptguard",
  "args": [
    "mcp",
    "-t",
    "stdio"
  ],
  "env": {
    "PROMPTGUARD_API_KEY": ""
  }
}