Guardrly

by fishcoco-code

253 downloads Not rated yet
GitHub

About

Non-invasive AI Agent operation monitoring — audit every API call your agent makes to Shopify, Meta Ads, and more. Real-time alerts, audit logs, and operation history. Works with Claude Desktop, Cursor, and any MCP-compatible AI tool.

Explore

- Real-time interception — Every HTTP request your Agent makes passes through Guardrly first
- Automatic PII scrubbing — API keys, tokens, and sensitive data are removed before any data leaves your machine
- 100+ semantic rules — For Shopify Admin API and Meta Marketing API
- Risk-based alerts — Email notifications for Level 3 critical operations
- Complete audit trail — Query every Agent operation from your Dashboard

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Guardrly
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Mac / Linux:
\\\bash
curl -fsSL https://guardrly.com/install.sh | bash
\
\\

Windows (PowerShell):
\\\powershell
irm https://guardrly.com/install.ps1 | iex
\
\\

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "guardrly": {
            "guardrly": {
                "command": "guardrly",
                "args": [],
                "env": {
                    "GUARDRLY_API_KEY": "your_api_key_here",
                    "GUARDRLY_API_URL": "https://api.guardrly.com",
                    "HMAC_SECRET": "your_hmac_secret_here"
                }
            }
        }
    }
}

McpServers

{
    "guardrly": {
        "command": "guardrly",
        "args": [],
        "env": {
            "GUARDRLY_API_KEY": "your_api_key_here",
            "GUARDRLY_API_URL": "https://api.guardrly.com",
            "HMAC_SECRET": "your_hmac_secret_here"
        }
    }
}
Guardrly is a non-invasive MCP Server that monitors every API call your AI Agent makes to external platforms like Shopify and Meta Ads.

Why Guardrly?

AI Agents like Claude Code and Cursor can execute hundreds of API calls autonomously. Without visibility, you risk: - Unexpected data modifications (deleted products, cancelled orders) - Platform bans from rate limit violations - No audit trail when something goes wrong

Key Features

- Real-time interception — Every HTTP request your Agent makes passes through Guardrly first - Automatic PII scrubbing — API keys, tokens, and sensitive data are removed before any data leaves your machine - 100+ semantic rules — For Shopify Admin API and Meta Marketing API - Risk-based alerts — Email notifications for Level 3 critical operations - Complete audit trail — Query every Agent operation from your Dashboard

Supported Platforms

- Shopify Admin API — 50 rules, 10 operation categories - Meta Ads API — 50 rules, 10 operation categories - Generic HTTP — Basic logging for any other API

Quick Install

Mac / Linux: \\\bash curl -fsSL https://guardrly.com/install.sh | bash \\\ Windows (PowerShell): \\\powershell irm https://guardrly.com/install.ps1 | iex \\\

Links

- Website: guardrly.com - Dashboard: app.guardrly.com - Docs: guardrly.com/docs - GitHub: github.com/fishcoco-code/guardrly-mcp

Pricing

Free tier available. Paid plans start at $49/month.
No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.