Guardrly Mcp

Overview

Guardrly Mcp is a Model Context Protocol server that provides non-invasive monitoring and auditing of AI Agent API calls to platforms like Shopify and Meta Ads. It integrates directly into AI assistants as a set of callable tools, giving you visibility into every interaction your agent makes with external services.

The server runs locally on your machine via the uvx guardrly command, which starts the Python package and communicates through MCP over stdio. You'll need to provide GUARDRLY_API_KEY and HMAC_SECRET as environment variables to authenticate with the service. Version v0.1.3 is the current release, published under the MIT license with source code available at fishcoco-code/guardrly-mcp on GitHub.

Guardrly Mcp appears in the AI & Agents category on mcp.site and works with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain this project, you can claim this listing to verify your ownership, earn the Verified badge, and keep information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "guardrly_mcp": {
      "command": "uvx",
      "args": [
        "guardrly"
      ],
      "env": {
        "GUARDRLY_API_KEY": "<guardrly-api-key>",
        "HMAC_SECRET": "<hmac-secret>"
      }
    }
  }
}

Requires GUARDRLY_API_KEY, HMAC_SECRET