Back to Directory/Monitoring & Observability

io.github.fishcoco-code/guardrly-mcp

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

Monitoring & ObservabilityPythonv0.1.3

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.

Installation

Source-derived launch command. Check the maintainer’s required arguments and credentials before running:

bash
uvx guardrly

Set up in your AI client

Merge this template into ~/Library/Application Support/Claude/claude_desktop_config.json. Keep existing servers. Add any arguments, credentials, and permissions required by the maintainer; this template has not been install-tested.

json
{
  "mcpServers": {
    "io-github-fishcoco-code-guardrly-mcp": {
      "command": "uvx",
      "args": [
        "guardrly"
      ]
    }
  }
}

Restart Claude Desktop completely for changes to take effect. Confirm the server appears connected in the client’s tool list, then try a read-only example from its documentation.

Claude Desktop setup reference

Package

guardrlypypi

Compatible MCP Clients

io.github.fishcoco-code/guardrly-mcp works with any MCP-compatible client. Copy the config snippet from the Configuration section above and add it to the file shown for your client, then restart the application.

  • Claude Desktop~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop completely for changes to take effect.
  • Cursor~/.cursor/mcp.jsonRestart Cursor for changes to take effect.
  • VS Code.vscode/mcp.jsonReload VS Code window for changes to take effect.
  • Windsurf~/.codeium/windsurf/mcp_config.jsonRestart Windsurf for changes to take effect.
  • Claude Code.mcp.jsonSave at the project root, then start Claude Code in that project and review the MCP server approval prompt. Keep real credentials out of shared files.

Learn More