# mcp-audit

> mcp-audit — coffeegrind123-mcp-audit. Use this tool when you need to audit and improve the usability of an MCP server for AI agents. It solves problems related to agent usability by identifying and fixing issues using mcpgrade, and provides output on the improved grade. The tool takes an MCP server as input and returns a report on the upgraded server's usability, making it ideal for use cases where agent performance and reliability are critical.

Canonical page: https://skillsregistry.net/skills/coffeegrind123-mcp-audit  
JSON: https://api.skillsregistry.net/v1/skills/coffeegrind123-mcp-audit

## Description

Claude Code skill: audit an MCP server for agent usability with mcpgrade, fix what it finds, prove the grade moved

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/coffeegrind123/mcp-audit)

## 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": "coffeegrind123-mcp-audit"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/coffeegrind123-mcp-audit` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/coffeegrind123-mcp-audit/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