claude-setup-audit-mcp
# claude-setup-audit-mcp
An MCP server that tells you why Claude Code keeps ignoring your instructions, then helps you fix it.
Three tools:
`audit_claude_setup` scores a repo's Claude Code setup from 0 to 100 and lists what to fix in order. It checks whether CLAUDE.md exists, whether it lists commands and do-not rules, whether it is short enough to be read, whether it leaks a credential, whether your subagents have proper frontmatter and restricted tools, whether you have skills, hooks, and an .mcp.json, and whether settings.local.json is git-ignored.
`scaffold_agent` writes a complete `.claude/agents/<name>.md` from a one-line job description, with frontmatter, a procedure, a report format, and do-not rules.
`hook_recipes` returns three settings.json hooks that work on Windows and macOS: a formatter after every edit, a guard that blocks destructive shell commands, and a bell when Claude stops and is waiting on you.
## Install
Add to `.mcp.json` in your repo (or to Claude Code with `claude mcp add`):
```json
{
"mcpServers": {
"claude-setup-audit": {
"command": "npx",
"args": ["-y", "claude-setup-audit-mcp"]
}
}
}
```
On Windows, use `"command": "cmd", "args": ["/c", "npx", "-y", "claude-setup-audit-mcp"]`.
Then in Claude Code: "audit this repo's Claude setup". It calls the tool and reads you the findings.
## Run from source
```
npm install
npm run build
npm run smoke # audits ../claude-code-starter-pack and checks all three tools
```
No network calls, no telemetry. It reads files under the path you give it and nothing else.
## What the score means
Under 40: Claude is working from nothing. Start with CLAUDE.md and the commands section.
40 to 70: the basics exist but nothing is enforced. Add hooks and restrict agent tools.
Over 70: the setup is sound. The remaining gains come from agents written for your specific repeated jobs, which is what I do for teams. Details at github.com/shadrach16.
A ready-made starting point is the [claude-code-starter-pack](https://github.com/shadrach16/claude-code-starter-pack).
MIT licensed. Built by Tunde Oluwamo.
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: one audits the setup, one scaffolds an agent file, and one returns hook recipes. There is no meaningful overlap or ambiguity between them.
All names use lowercase snake_case and two follow a verb_noun pattern (audit_claude_setup, scaffold_agent). hook_recipes is noun_noun, so the pattern is mostly consistent with a minor deviation.
Three tools is a well-scoped set for an audit-focused server. Each tool earns its place without redundancy or unnecessary surface area.
The audit tool covers the full setup surface, and there are helpers for agent files and hooks. However, other audited areas like CLAUDE.md, skills, .mcp.json, and .gitignore have no corresponding scaffold or recipe tool, leaving notable gaps for remediation.