Maiife Toolkit

Open-source AI governance tools. Each works standalone as an MCP server or CLI — together they form a governance mesh.

npm scope License: Apache 2.0 PRs Welcome maiife-toolkit MCP server

maiife-toolkit MCP server

Built by Maiife — Enterprise AI Control Plane.

Requirements

Node.js >= 18
npm or pnpm

Installation

# Install individual tools via npm
npm install -g @maiife-ai-pub/probe
npm install -g @maiife-ai-pub/mcp-audit

# Or run directly with npx (no install needed)
npx @maiife-ai-pub/probe scan
npx @maiife-ai-pub/mcp-audit scan

Tools

Package	Description	Published
`@maiife-ai-pub/shared`	Shared types and formatters used by all toolkit packages	✅
`@maiife-ai-pub/probe`	AI environment scanner — discover IDE extensions, MCP servers, agent frameworks, API keys, local models	✅
`@maiife-ai-pub/mcp-audit`	MCP server security scanner — score configs on permissions, data sensitivity, blast radius	✅
`@maiife-ai-pub/ai-stack`	"What's Your AI Stack?" — shareable profile card of your AI toolkit	✅
`@maiife-ai-pub/mcp-doctor`	MCP health check & auto-fixer — brew doctor for your MCP setup	✅
`@maiife-ai-pub/ai-journal`	Personal AI usage diary — track how you use AI, get reflective insights	✅
`@maiife-ai-pub/context-sync`	Cross-tool AI memory sync — one context.json, synced to Cursor, Claude, MCP	✅
`@maiife-ai-pub/prompt-score`	Prompt quality analyzer — score, improve, and lint your AI prompts	✅
`@maiife-ai-pub/eval`	LLM-as-judge evaluation engine — score agent outputs with structured rubrics	✅
`@maiife-ai-pub/trace`	Agent workflow tracer — trace, view, and analyze execution spans	✅
`@maiife-ai-pub/cost`	AI spend calculator + optimizer — unified cost report across vendors	✅
`@maiife-ai-pub/prompt-craft`	Gamified prompt coach — levels, streaks, badges for prompt improvement	✅
`@maiife-ai-pub/sub-audit`	Personal AI subscription auditor — find waste in your AI spending	✅
`@maiife-ai-pub/model-match`	Personal model recommender — find the best model for YOUR tasks	✅
`@maiife-ai-pub/weekly-ai-report`	AI week in review — Spotify Wrapped for your AI usage, weekly	✅

Quick Start

# Scan your AI environment
npx @maiife-ai-pub/probe scan

# Audit your MCP server security
npx @maiife-ai-pub/mcp-audit scan

# Generate your AI Stack profile card
npx @maiife-ai-pub/ai-stack --format svg --output my-stack.svg

# Health check your MCP servers
npx @maiife-ai-pub/mcp-doctor check

# Log an AI interaction
npx @maiife-ai-pub/ai-journal log --tool claude --task coding --duration 30

# Sync AI context across tools
npx @maiife-ai-pub/context-sync push

# Score your AI prompts
npx @maiife-ai-pub/prompt-score analyze --input prompt.txt

# Evaluate agent outputs with rubrics
npx @maiife-ai-pub/eval score --rubric code-review --input review.txt

# Trace agent workflows
npx @maiife-ai-pub/trace list --days 7

# Track AI spend across vendors
npx @maiife-ai-pub/cost report --period last-30d

# Gamified prompt coaching
npx @maiife-ai-pub/prompt-craft score --input prompt.txt

# Audit AI subscriptions for waste
npx @maiife-ai-pub/sub-audit

# Find the best model for your tasks
npx @maiife-ai-pub/model-match recommend --task coding

# Generate your AI week in review
npx @maiife-ai-pub/weekly-ai-report generate

Use as MCP Servers

Each tool exposes an MCP server via Model Context Protocol. Add them to your Claude Desktop, Cursor, or any MCP-compatible client.

Config file location:

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

{
  "mcpServers": {
    "maiife-probe": {
      "command": "npx",
      "args": ["@maiife-ai-pub/probe", "mcp"]
    },
    "maiife-mcp-audit": {
      "command": "npx",
      "args": ["@maiife-ai-pub/mcp-audit", "serve"]
    },
    "maiife-mcp-doctor": {
      "command": "npx",
      "args": ["@maiife-ai-pub/mcp-doctor", "serve"]
    },
    "maiife-ai-stack": {
      "command": "npx",
      "args": ["@maiife-ai-pub/ai-stack", "serve"]
    },
    "maiife-prompt-score": {
      "command": "npx",
      "args": ["@maiife-ai-pub/prompt-score", "serve"]
    },
    "maiife-eval": {
      "command": "npx",
      "args": ["@maiife-ai-pub/eval", "serve"]
    },
    "maiife-trace": {
      "command": "npx",
      "args": ["@maiife-ai-pub/trace", "serve"]
    },
    "maiife-cost": {
      "command": "npx",
      "args": ["@maiife-ai-pub/cost", "serve"]
    },
    "maiife-context-sync": {
      "command": "npx",
      "args": ["@maiife-ai-pub/context-sync", "serve"]
    },
    "maiife-prompt-craft": {
      "command": "npx",
      "args": ["@maiife-ai-pub/prompt-craft", "serve"]
    },
    "maiife-sub-audit": {
      "command": "npx",
      "args": ["@maiife-ai-pub/sub-audit", "serve"]
    },
    "maiife-model-match": {
      "command": "npx",
      "args": ["@maiife-ai-pub/model-match", "serve"]
    }
  }
}

MCP Tools Summary

Server	Tools	Description
`probe`	`probe_scan`, `probe_list_models`, `probe_list_extensions`, `probe_check_keys`	Scan AI environment
`mcp-audit`	`scan_servers`, `score_server`	Audit MCP security
`mcp-doctor`	`mcp_checkup`, `mcp_fix`, `mcp_status`	Diagnose & fix MCP configs
`ai-stack`	`ai_stack_scan`	Generate AI stack profile
`prompt-score`	`prompt_analyze`, `prompt_improve`, `prompt_track`	Score & improve prompts
`eval`	`eval_score`, `eval_batch`, `eval_compare`	Evaluate LLM outputs
`trace`	`trace_list`, `trace_view`, `trace_analyze`	Trace agent workflows
`cost`	`cost_report`, `cost_optimize`	Track & optimize AI spend
`context-sync`	`context_get`, `context_set`, `context_push`, `context_pull`	Sync AI context
`prompt-craft`	`craft_score`, `craft_improve`, `craft_profile`, `craft_challenge`	Gamified prompt coaching
`sub-audit`	`sub_audit_run`	Audit AI subscriptions
`model-match`	`model_compare`, `model_recommend`	Recommend models

Contributing

Contributions are welcome! Here's how to get started:

Fork the repo on GitHub
Create a branch: git checkout -b feat/my-improvement
Make your changes — each package lives in packages/<name>/
Run tests: pnpm test
Open a PR against main — describe what you changed and why

Please follow the existing code style (TypeScript, ESM, Vitest for tests). Each package should work as both a CLI and an MCP server where applicable.

License

Apache 2.0 — free to use, modify, and distribute.

Part of the Maiife platform — Enterprise AI Control Plane.

maiife-toolkit