claude-setup-audit-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| audit_claude_setupA | Scores a repository's Claude Code setup (CLAUDE.md, .claude/agents, .claude/skills, hooks in settings.json, .mcp.json, .gitignore) from 0 to 100 and lists what to fix, in order. Pass the repo root path. |
| scaffold_agentA | Returns a complete .claude/agents/.md for a role, with frontmatter (name, description, tools), a procedure, a report format, and do-not rules. Save the returned text to .claude/agents/.md. |
| hook_recipesA | Returns three tested settings.json hook recipes (format after edit, block destructive commands, bell on stop) that work on Windows and macOS. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
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.