MCP Safety Warden

Overview

MCP Safety Warden is an MCP proxy that adds security scanning, behavioral profiling, risk gating, and safe tool call execution to your AI workflows. By integrating with the Model Context Protocol, it lets Claude, Cursor, VS Code, and other MCP clients use these security capabilities as native tools without manual integration.

The server runs locally on your machine via the uvx mcpsafetywarden command. It requires no authentication and works immediately out of the box with the Python package mcpsafetywarden. The latest release is v1.4.18, with full source code available at gautamvarmadatla/mcpsafetywarden on GitHub.

MCP Safety Warden is listed in the Security category on mcp.site and works with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain this server, claim your listing to earn the Verified badge and ensure the information stays current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "mcp_safety_warden": {
      "command": "uvx",
      "args": [
        "mcpsafetywarden"
      ]
    }
  }
}