Agent Audit

Verified Integration

Author: @detecting•Category: ServerApplication

GitHub Repository

JSON-RPC 2.0

Protocol Standard

Sub-second

Execution Latency

Active

Operational Status

Client Configuration

— Connect Agent Audit to Claude Desktop or Cursor in seconds

{
  "mcpServers": {
    "agent-audit": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-agent-audit"
      ],
      "env": {}
    }
  }
}

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).

Architecture & Capabilities

System Overview

Scans MCP server configurations and AI agent tooling for common security vulnerabilities like prompt injection, command injection, and hardcoded secrets.

Indexed Date

7/21/2026

License

Open Source

Protocol Layer

stdio / SSE RPC

Frequently Asked Questions

Architecture and operational details for Agent Audit

Agent Audit is a specialized security scanner for MCP servers and AI agent tooling. It identifies common and critical vulnerabilities like prompt injection, command injection, and exposed secrets in your configurations.

Related MCP Servers

Browse all servers →

@configuring

0xArchive

Provides comprehensive historical and real-time crypto market data, including orderbooks, trades, candles, and more, from Hyperliquid, HIP-3, and Lighter.xyz.

MCP Server5 FAQs

Learn more

@spawning

0xGasless

Facilitates gasless blockchain transactions and interactions directly from Claude AI conversations.

MCP Server4 FAQs

Learn more

@spawning

0xGasless

Bridges Claude AI with blockchain networks, enabling gasless transactions, swaps, and transfers directly from natural language conversations.

MCP Server5 FAQs

Learn more