promptwall

vtino17/promptwall

★ 0 stars Python Security Updated today

A firewall for LLM traffic: detect prompt injection, jailbreaks, and secret/PII leaks. Zero-dependency Python library + CLI + MCP server.

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": {
    "promptwall": {
      "command": "uvx",
      "args": [
        "promptwall"
      ]
    }
  }
}

Or install with pip: pip install promptwall

README Excerpt

**A firewall for LLM traffic.** PromptWall inspects the text flowing *into* and *out of* a Large Language Model and catches the things that get apps built on LLMs into trouble: - 🧨 **Prompt injection** — "ignore all previous instructions and…" - 🔓 **Jailbreaks** — DAN, "developer mode", "you are now unrestricted", roleplay bypasses

Topics

ai-safetyai-securityguardrailsjailbreakllmllm-securitymcpprompt-injectionpythonsecurity

promptwall

Quick Install

README Excerpt

Topics

Related Security Servers