ai-first-toolkit MCP — Use Cases, Install & Live Demo

Why use it

Key features

AI-readiness audit — scores a repo on structure, docs, tests, agent-friendliness
Re-engineering recipes to improve AI-ergonomics of legacy code
Bootstrap skill for greenfield projects with sane defaults
Cross-agent: works in Claude Code and Codex
TypeScript-based tooling

Live Demo

What it looks like in practice

ai-first-toolkit-skill.replay ▶ ready

0/0

Install

Pick your client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "ai-first-toolkit-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/techwolf-ai/ai-first-toolkit",
        "~/.claude/skills/ai-first-toolkit"
      ],
      "_inferred": true
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "ai-first-toolkit-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/techwolf-ai/ai-first-toolkit",
        "~/.claude/skills/ai-first-toolkit"
      ],
      "_inferred": true
    }
  }
}

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "ai-first-toolkit-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/techwolf-ai/ai-first-toolkit",
        "~/.claude/skills/ai-first-toolkit"
      ],
      "_inferred": true
    }
  }
}

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "ai-first-toolkit-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/techwolf-ai/ai-first-toolkit",
        "~/.claude/skills/ai-first-toolkit"
      ],
      "_inferred": true
    }
  }
}

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "ai-first-toolkit-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/techwolf-ai/ai-first-toolkit",
        "~/.claude/skills/ai-first-toolkit"
      ]
    }
  ]
}

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

{
  "context_servers": {
    "ai-first-toolkit-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/techwolf-ai/ai-first-toolkit",
          "~/.claude/skills/ai-first-toolkit"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

claude mcp add ai-first-toolkit-skill -- git clone https://github.com/techwolf-ai/ai-first-toolkit ~/.claude/skills/ai-first-toolkit

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use ai-first-toolkit

How to audit a codebase for AI-agent readiness

👤 Tech leads preparing a codebase for heavy AI-assisted work ⏱ ~45 min intermediate

When to use: Before the team commits to doing a lot of feature work through Claude or Codex.

Prerequisites

Skill cloned — git clone https://github.com/techwolf-ai/ai-first-toolkit ~/.claude/skills/ai-first-toolkit

Flow

Run the audit

Audit this repo for AI-agent readiness. Score each dimension and list the top 5 friction points.✓ Copied

→ Dimension scores + specific files to fix
Prioritize fixes

Which of those fixes would give the biggest agent-effectiveness lift per hour of work?✓ Copied

→ Ranked list with effort/impact
Apply the top fix

Apply fix #1 end-to-end — edit files, update docs, add tests.✓ Copied

→ Diff + confirmation

Outcome: A concrete improvement plan and at least one applied fix making the repo friendlier to AI agents.

Pitfalls

Audit turns into a generic 'improve docs' blob — Ask for file:line level findings, not abstract advice

Combine with: filesystem · github

Bootstrap a new AI-friendly project

👤 Founders or ICs starting a new repo ⏱ ~30 min beginner

When to use: Day zero of a new project, before you pick bad defaults that will haunt you.

Flow

State the project

Bootstrap a new TypeScript API project using ai-first-toolkit defaults. Purpose: internal billing API.✓ Copied

→ Proposed folder structure, tsconfig, scripts, README skeleton
Scaffold the files

Create the files. Include AGENTS.md and CLAUDE.md with the relevant codebase notes.✓ Copied

→ Repo files materialized
First commit

Initialize git and make the first commit with a clean message.✓ Copied

→ Clean initial repo

Outcome: A new repo that's friendly to both humans and AI agents from commit 0.

Pitfalls

Scaffolding imports dependencies you don't want — Ask Claude to list dependencies before installing — accept each one

Combine with: github · filesystem

Re-engineer a messy module for AI readability

👤 Engineers paying down tech debt one module at a time ⏱ ~60 min advanced

When to use: You've isolated a module that Claude keeps getting wrong — usually a sign its structure isn't agent-legible.

Flow

Diagnose the module

Look at src/billing/. What about this code makes it hard for an agent to edit safely?✓ Copied

→ Specific red flags: indirection, hidden state, long functions
Plan the refactor

Propose a 3-step refactor that improves agent-legibility without changing public API.✓ Copied

→ Stepwise plan with diff sketches
Execute step 1

Apply step 1. Keep tests green.✓ Copied

→ PR-sized diff

Outcome: A module that Claude can actually reason about on the next iteration.

Pitfalls

Over-refactor and break behaviors you didn't mean to — Insist on public API stability and run tests after each step

Combine with: filesystem · github

Combinations

Pair with other MCPs for X10 leverage

ai-first-toolkit-skill + filesystem

Audit scans the repo; filesystem is needed to actually read it

Walk the repo and score AI-readiness; report findings file-by-file.✓ Copied

ai-first-toolkit-skill + github

Open a PR with the proposed AGENTS.md / CLAUDE.md additions

Apply the audit's top 3 fixes and open a PR titled 'AI-first improvements'.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call
ai-readiness-audit	repo root	Pre-investment in AI-heavy workflows
ai-first-bootstrap	project spec (lang, purpose, stack)	Greenfield projects
re-engineer-module	module path + goals	When a module resists agent edits

Cost & Limits

What this costs to run

API quota: none beyond your LLM provider
Tokens per call: 5–20k for an audit of a medium repo
Monetary: free, open source
Tip: Scope audits to a subtree rather than the whole monorepo

Security

Permissions, secrets, blast radius

Credential storage: none

Data egress: none beyond what filesystem/github tools do

Troubleshooting

Common errors and fixes

Audit is too abstract

Re-prompt with a concrete dimension: 'evaluate just the test layout' or 'just the module boundaries'.

Bootstrap picks wrong language

Always state language+runtime+build tool in the first prompt.

Alternatives

ai-first-toolkit vs others

Alternative	When to use it instead	Tradeoff
init (built-in)	You just need a CLAUDE.md and don't care about the rest	Narrower scope
antivibe-skill	You want the opposite lens — critique of AI-shaped sludge	Diagnostic, not prescriptive

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills