mcp-audit

abregoarthur-star/mcp-audit

★ 0 stars JavaScript Security Updated today

Security auditor for Model Context Protocol (MCP) servers — detects prompt injection, tool poisoning, lethal trifecta capability combos, and other AI-native vulnerabilities

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": {
    "mcp-audit": {
      "command": "npx",
      "args": [
        "-y",
        "abregoarthur-star/mcp-audit"
      ]
    }
  }
}

README Excerpt

A security auditor for **Model Context Protocol (MCP)** servers. Scans tool, resource, and prompt definitions for AI-native security issues — prompt injection, tool poisoning, dangerous capability combinations, schema permissiveness, and more. > Why this exists: MCP servers ship arbitrary text directly into the host LLM's context. A malicious or sloppy server can manipulate any agent that connects to it. As the MCP ecosystem grows, the surface for prompt injection, tool poisoning, and "lethal tr

Tools (5)

baselinebearerheadershighurl

mcp-audit

Quick Install

README Excerpt

Tools (5)

Related Security Servers