mcpField
G
Guardrly

Guardrly

Local
github.com/fishcoco-codeDeveloper Tools0
Repository

About Guardrly

Guardrly is a monitoring layer for AI Agent operations on external platforms, aimed at users who need visibility and alerts. It records API activity, creates audit logs, and scrubs PII locally before cloud transfer.

Key features

  1. 01Record external API operations
  2. 02Create human-readable audit trails
  3. 03Alert on risky operations
  4. 04Generate structured operation logs
  5. 05Scrub PII locally before cloud transfer

Use cases

  1. 01Review an Agent's actions on external platforms
  2. 02Receive alerts about dangerous operations
  3. 03Keep operation records for account appeals
  4. 04Limit PII sent to the cloud

MCP support

Guardrly is identified as an MCP server and is described as working with Claude Desktop, Cursor, and MCP-compatible AI tools. The input does not specify its MCP tools or protocol behavior.

#monitoring#security#shopify#meta-ads#audit-log#observability#ai-agent#claude#cursor

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "guardrly": {
      "command": "uvx",
      "args": [
        "guardrly"
      ],
      "env": {
        "GUARDRLY_API_KEY": "<GUARDRLY_API_KEY>",
        "GUARDRLY_API_URL": "<GUARDRLY_API_URL>",
        "HMAC_SECRET": "<HMAC_SECRET>"
      }
    }
  }
}
Run commanduvx guardrly
Environment variables to set
GUARDRLY_API_KEYSecretYour Guardrly API key from app.guardrly.com/settings
GUARDRLY_API_URLGuardrly API endpoint
HMAC_SECRETSecretYour HMAC secret from app.guardrly.com/settings MCP Configuration panel

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiguardrly0.1.3

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.