guardrly-mcp

fishcoco-code/guardrly-mcp
Community

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

Non-invasive AI Agent monitoring — audit every API call to Shopify, Meta Ads, and more

README.md

mcp-name: io.github.fishcoco-code/guardrly-mcp

Guardrly

Website: guardrly.com

Guardrly is a non-invasive AI Agent operation monitoring layer that intercepts, records, and alerts on every API call an AI Agent makes to external platforms - giving users full visibility into what their Agent did, when, and why.

Features

  • Visibility - Turn Agent black-box operations into a human-readable audit trail
  • Protection - Alert on dangerous operations before damage is done
  • Evidence - Generate structured operation logs usable as appeal evidence for banned accounts
  • Compliance - PII is scrubbed at the local layer before any data reaches the cloud

Installation

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

# Windows (PowerShell)
iwr https://guardrly.com/install.ps1 | iex

Development Setup

# Install dependencies
poetry install

# Copy environment template
cp .env.example .env
# Edit .env with your credentials

# Run API server
poetry run uvicorn api.main:app --reload

License

MIT License. See LICENSE for details.

Related MCP servers

Browse all →