promptguard

Hayatelin/promptguard

★ 0 stars Python AI/LLM Updated today

Security pre-flight for AI agents - scans agent configs, system prompts, tool definitions and MCP servers for prompt-injection and over-privileged tools. Zero dependencies.

View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "promptguard": {
      "command": "uvx",
      "args": [
        "promptguard"
      ]
    }
  }
}

Or install with pip: pip install promptguard

README Excerpt

<h1 align="center">promptguard</h1> <p align="center"> <strong>Catch prompt-injection and over-privileged tools before you ship your AI agent.</strong> </p> <p align="center"> A zero-dependency security pre-flight for AI agents — it scans agent configs, system prompts, tool/function definitions, and MCP server configs for

Topics

agent-securityai-agentsai-securityappsecclidevsecopsllm-securitymcpprompt-injectionpython

promptguard

Quick Install

README Excerpt

Topics

Related AI/LLM Servers