Guardian Mcp

Overview

Guardian Mcp is a Model Context Protocol server that provides runtime AI-threat screening for coding agents. It analyzes and scans tool calls, outputs, and documentation to identify potential security risks, helping protect your development workflow from unwanted AI behavior. This is a paid service designed to add a security layer to agent-driven coding.

The server runs locally on your machine via the ethicore-guardian-mcp Python package, installed with uvx. It communicates over stdio and requires an API key for authentication. The latest release is v0.1.2.

Guardian Mcp is listed in the Development category and works with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and others. If you maintain Guardian Mcp, you can claim this listing to verify ownership and keep information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "guardian_mcp": {
      "command": "uvx",
      "args": [
        "ethicore-guardian-mcp"
      ]
    }
  }
}