Agent Security Harness
Verified IntegrationClient Configuration
— Connect Agent Security Harness to Claude Desktop or Cursor in seconds{
"mcpServers": {
"agent-security-harness": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-agent-security-harness"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
Provides a comprehensive, open-source security testing framework for multi-agent AI systems in critical enterprise environments.
7/21/2026
Open Source
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for Agent Security Harness
It's the first open-source security testing framework designed specifically for multi-agent AI systems in critical enterprise and infrastructure environments. It verifies if autonomous agents can be trusted to take consequential action under adversarial conditions.
Related MCP Servers
Browse all servers →Provides comprehensive historical and real-time crypto market data, including orderbooks, trades, candles, and more, from Hyperliquid, HIP-3, and Lighter.xyz.
Facilitates gasless blockchain transactions and interactions directly from Claude AI conversations.
Bridges Claude AI with blockchain networks, enabling gasless transactions, swaps, and transfers directly from natural language conversations.