Agent Security
Verified IntegrationClient Configuration
— Connect Agent Security to Claude Desktop or Cursor in seconds{
"mcpServers": {
"agent-security": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-agent-security"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
Secures AI agent workflows by providing comprehensive security scanning, prompt injection and secret leak detection, and agent permission auditing.
7/21/2026
Open Source
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for Agent Security
The Model Context Protocol (MCP) is the foundational framework for AI agent communication. Agent Security is built on MCP to seamlessly secure agent interactions, configurations, and tool definitions specifically within MCP environments.
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.