# guardrly-mcp

> guardrly-mcp — fishcoco-code-guardrly-mcp. Use this tool when you need to monitor AI agent operations non-invasively, particularly for Claude Desktop, Cursor, and other MCP-compatible tools. It solves problems related to AI performance tracking and debugging, providing insights into AI tool functionality. The guardrly-mcp tool accepts AI agent data as input and outputs operational metrics, making it ideal for development and testing contexts where AI tool performance needs to be optimized.

Canonical page: https://skillsregistry.net/skills/fishcoco-code-guardrly-mcp  
JSON: https://api.skillsregistry.net/v1/skills/fishcoco-code-guardrly-mcp

## Description

Non-invasive AI Agent operation monitoring — MCP Server for Claude Desktop, Cursor, and any MCP-compatible AI tool

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/fishcoco-code/guardrly-mcp)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "fishcoco-code-guardrly-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/fishcoco-code-guardrly-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/fishcoco-code-guardrly-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt