Guardrly MCP Server

@fishcoco-code

代码仓库

基本信息

分类

开发工具

传输方式

stdio

作者

fishcoco-code

提交者

Fish DIY Weave

关于 Guardrly MCP Server

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.

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

Guardrly MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "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 MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Guardrly?

Guardrly is a non-invasive MCP Server that monitors every API call your AI Agent makes to external platforms like Shopify and Meta Ads, providing real-time interception, automatic PII scrubbing, and risk-based alerts for Agent operations.

How to use Guardrly?

Install via a one-liner for Mac/Linux or Windows PowerShell (as shown in the README). After installation, configure it via the Guardrly Dashboard at app.guardrly.com; no further configuration steps are described.

Key features of Guardrly

Real-time interception of every HTTP request
Automatic PII scrubbing (API keys, tokens, sensitive data)
100+ semantic rules for Shopify and Meta Ads APIs
Risk-based email alerts for Level 3 critical operations
Complete audit trail queryable from Dashboard
Supports Shopify Admin API, Meta Ads API, and generic HTTP logging

Use cases of Guardrly

Preventing unexpected data modifications by AI Agents (e.g., deleted products, cancelled orders)
Avoiding platform bans from rate limit violations
Creating an audit trail for all Agent operations
Monitoring autonomous API calls made by Claude Code or Cursor

常见问题

What does Guardrly do differently from standard logging?

Guardrly intercepts every HTTP request in real-time, strips sensitive data automatically, and applies 100+ semantic rules to flag risky operations before they happen.

Which platforms does Guardrly support?

Shopify Admin API (50 rules, 10 operation categories), Meta Ads API (50 rules, 10 operation categories), and generic HTTP logging for any other API.

Does Guardrly require any code changes to my AI agent?

No, it is described as non-invasive; it runs as an MCP Server that intercepts API calls without modifying your agent code.

Where does my data go when using Guardrly?

PII is scrubbed automatically before any data leaves your machine; a queryable audit trail is stored in the Guardrly Dashboard.

Is there a free tier available?

Yes. Free tier is available; paid plans start at a price not specified in the README (refer to guardrly.com).

开发工具分类下的更多 MCP 服务器

Meticulous

Eddyter AI Rich Text Editor MCP

EddyterAI

Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R

Mcp-Warden

ermoluk

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

Launchdog

Devin Starks

Launch your product from your AI agent. Connect Claude Code, Codex, Cursor or ChatGPT to Launchdog over MCP and your agent drafts the listing, picks a launch week and books it. 50 launches a week, ranked only by human vo

Casefile

azimov777

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.