About pkgdiet
pkgdiet is a dependency-policy CLI and local MCP server for JavaScript and TypeScript projects using AI coding agents. It evaluates packages against a shared repository policy and can intercept installs or enforce the policy in CI.
Key features
- 01Policy checks for npm packages
- 02Install interception through agent hooks
- 03Dependency health and size audits
- 04GitHub Actions policy gate
- 05Alternative package suggestions
Use cases
- 01Block deprecated or vulnerable installs
- 02Review dependencies proposed by coding agents
- 03Check new packages before merging a PR
MCP support
The local MCP server exposes `check_dependency` for policy verdicts and `suggest_alternative` for package alternatives.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project README🥗 PkgDiet
Dependency policy for AI-assisted JavaScript and TypeScript development.
Put your node_modules on a diet.
The Problem: AI coding agents (Claude Code, Codex, Cursor, Windsurf, Cline) propose nonexistent, deprecated, vulnerable, or typosquatted packages. There is no built-in mechanism to stop them from running the install.
The Solution: PkgDiet intercepts every npm install / pnpm add / yarn add command your AI agent generates — using native agent hook APIs — and blocks unapproved installs before they execute.
🔒 Live Proof
Run this to see PkgDiet block real risky AI-generated dependencies in your terminal:
npx [email protected] demo
Example output:
🔒 PkgDiet — Live AI Dependency Enforcement Demo
Simulating what happens when an AI agent tries to install these packages.
🟡 WARNING — moment
Context: AI suggested this for date formatting
Score: 100/100
Reason: Efficiency Flag: Better alternatives exist for moment.
Use this: dayjs, date-fns
🔴 BLOCKED — request
Context: AI suggested this for HTTP requests
Score: 15/100
Reason: Health score 15 is below minimum allowed (60).
Use this: undici, native fetch
CVEs: GHSA-p8p7-x288-28g6
🔒 PkgDiet blocked this risky AI-generated dependency before install.
🔴 BLOCKED — node-uuid
Context: AI suggested this for UUID generation
Score: 15/100
Reason: Health score 15 is below minimum allowed (60).
Use this: crypto.randomUUID(), uuid
🔒 PkgDiet blocked this risky AI-generated dependency before install.
🟡 WARNING — lodash
Context: AI suggested this for array utilities
Score: 80/100
Reason: Efficiency Flag: Better alternatives exist for lodash.
Use this: lodash-es, native JS
📊 Demo Summary: 2 blocked, 2 warned
These checks run automatically before every npm install in your AI agent.
Setup: npx [email protected] init
For machine-readable CI proof:
npx [email protected] demo --json
🚀 One-Command Setup
npx [email protected] init
This single command creates:
| File | Purpose |
|---|---|
.pkgdietrc.json | Repository dependency policy |
.github/workflows/pkgdiet.yml | GitHub Actions CI gate |
.cursor/mcp.json | Cursor MCP server |
.cursor/rules/pkgdiet.mdc | Cursor always-applied enforcement rule |
.cursorrules | Cursor advisory rule (legacy) |
.windsurfrules | Windsurf advisory rule |
cline_mcp_settings.json | Cline MCP server |
.github/mcp.json | GitHub Copilot MCP |
CLAUDE.md | Claude Code advisory rule |
.claude/settings.json | Claude Code PreToolUse hook registration |
.claude/hooks/pkgdiet-install-guard.sh | Claude Code bash install guard |
.codex/hooks.json | Codex PreToolUse hook registration |
.codex/hooks/pkgdiet-install-guard.mjs | Codex Node.js install guard |
🛡️ Enforcement by Agent
PkgDiet uses each agent's native hook API to block installs — not just advisory rules:
| Agent | Enforcement Mechanism | What it blocks |
|---|---|---|
| Claude Code | PreToolUse bash hook (.claude/hooks/) | npm/pnpm/yarn install before execution |
| Codex (OpenAI) | PreToolUse Node.js hook (.codex/hooks/) | npm/pnpm/yarn install before execution |
| Cursor | MDC alwaysApply rule + MCP check_dependency | Prevents AI from writing install commands |
| Windsurf | .windsurfrules + MCP check_dependency | Prevents AI from writing install commands |
| Cline | MCP check_dependency | Blocks before install via tool call |
| GitHub Copilot | MCP check_dependency | Blocks before install via tool call |
| CI (GitHub Actions) | pkgdiet ci gate | Blocks PR merge if any new package fails policy |
How PreToolUse hooks work: When Claude Code or Codex generates a Bash tool call containing
npm install, the registered hook script runs first. If PkgDiet returns a non-zero exit code, the agent sees the denial reason and aborts the install — the command never runs.
🔄 The 3-Phase Policy Loop
PkgDiet uses a shared core engine (@pkgdiet/core) so all interfaces apply the same evaluation logic.
- Repository Policy: A single
.pkgdietrc.jsonfile dictates what is allowed, warned, or blocked for your project. - Agent Hook (Enforce): Native PreToolUse hooks for Claude Code and Codex intercept install commands before execution. MCP
check_dependencyinstructs other agents before they write the command. - CI Gate (Fallback):
npx pkgdiet ciruns in GitHub Actions, diffspackage.jsonagainst the base commit, and fails the PR if any added package violates policy.
🛠️ CLI Commands
Commands:
audit Audit existing dependencies for policy, health, size, and unused-package signals
check Evaluate npm packages against this repository's dependency policy
demo Show live proof that PkgDiet blocks risky AI-generated dependencies before install
mcp Start the MCP JSON-RPC server over stdio for MCP-compatible AI coding agents
ci Enforce policy for dependency changes introduced by this branch
init Set up PkgDiet — creates policy, CI workflow, and all AI agent configs
agent-setup Configure PkgDiet for AI coding agents (codex, cursor, claude-code, ...)
alternatives Browse the PkgDiet alternatives dataset
drift Scan project for dependency health drift over time
policy-check Validate the repository's .pkgdietrc.json policy
⚙️ Configuration (.pkgdietrc.json)
{
"minHealthScore": 70,
"warnHealthScore": 80,
"blockDeprecated": true,
"blockKnownVulnerabilities": true,
"blockTyposquats": false,
"requirePinnedVersions": true,
"maxPackageSizeBytes": 15728640,
"failOn": "BLOCK",
"securityMode": "fail-open",
"blockedPackages": ["moment", "request"],
"internalNamePrefixes": [],
"environments": {
"ci": { "minHealthScore": 80, "failOn": "BLOCK", "securityMode": "fail-closed" },
"dev": { "minHealthScore": 60, "failOn": "BLOCK", "securityMode": "fail-open" }
}
}
🤖 MCP Integration
PkgDiet acts as a local Model Context Protocol (MCP) server.
When your AI coding agent connects to PkgDiet, it gains access to:
check_dependency: Evaluates an npm package against your local.pkgdietrc.jsonpolicy and returns structuredALLOW,WARN, orBLOCKverdicts with evidence.suggest_alternative: Queries PkgDiet's curated dataset to find modern, lighter, and maintained alternatives for blocked packages.
Intelligence included (all free, no paid services):
- OSV vulnerability database — checks known CVEs for the package version
- npm registry provenance — verifies signed npm attestations
- Typosquat detection — edit-distance check against 15+ popular package names
- Lockfile pinning validation — requires exact version pins in CI
- Dependency confusion detection — blocks internal-prefix packages found on public registry
🔗 Documentation & Support
- GitHub Repository: om-tajne/pkgdiet
- Report an Issue: Issue Tracker
- License: MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.