mcp-audit
MCP Audit helps you identify what your AI agents can access before they go live.
MCP Audit scans your AI development tools and reveals critical information such as exposed secrets, API endpoints, and configured AI models. It provides insights into potential risks associated with your AI configurations, helping you take immediate action to secure your environment. The tool is designed to enhance compliance and security by generating AI-BOMs and flagging any vulnerabilities found during the scan.
Compatible with
Install
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"mcp-audit": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-mcp-audit"
]
}
}
}Config File Location
Mac: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/claude/claude_desktop_config.json
Some servers require additional setup - check the GitHub README for specific instructions.
Permissions