Universal-Poison-Armor

mzaid007/Universal-Poison-Armor

★ 0 stars Python AI/LLM Updated today

An open-source Model Context Protocol (MCP) server that acts as a security firewall for AI agents. It sanitizes data, web pages, and RAG documents against prompt injections and adversarial poisoning before they reach the LLM's context.

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": {
    "universal-poison-arm": {
      "command": "uvx",
      "args": [
        "universal-poison-armor"
      ]
    }
  }
}

Or install with pip: pip install universal-poison-armor

README Excerpt

**Universal Poison Armor** is an open-source, production-grade security framework and **Model Context Protocol (MCP)** server for AI agents, LLM pipelines, and RAG systems. It provides multi-layer protection against indirect prompt injection, zero-width Unicode steganography, adversarial suffixes (GCG attacks), tracking pixels / Markdown XSS, semantic dataset poisoning, and Consensus Poisoning / Sybil attacks.

Universal-Poison-Armor

Quick Install

README Excerpt

Related AI/LLM Servers