This server lets AI agents vet npm dependencies before installing them, get healthier alternatives, and inspect the active dependency policy.
check_dependency — Get an ALLOW / WARN / BLOCK verdict, health score, size impact, cost estimate, and reasons for a single package.
suggest_alternative — Get curated lighter or safer replacement packages for a given package.
get_policy — Retrieve the active PkgDiet dependency policy (e.g., min health score, security mode, blocked packages) for the current repository.
Enables CI/CD integration to parse package-lock.json diffs and block pull requests that introduce unhealthy dependencies.
Provides dependency intelligence for npm packages, enabling package health, size, maintenance, and alternative recommendations before installing or replacing dependencies.
Check any npm package in under 2 seconds. Get a ALLOW / WARN / BLOCK verdict, health score, size impact, cost estimate, and curated alternatives — before you install.
# Check a package before installing it
npx pkgdiet check moment
# Check multiple packages at once
npx pkgdiet check moment request lodash
# Audit your whole project
npx pkgdiet audit
# Wire up your AI coding agent (Cursor, Claude, Copilot, Windsurf…)
npx pkgdiet agent-setup --allRelated MCP server: dependency-health-mcp
🟡 moment
Health: 100/100
Verdict: WARN
Reasons: Efficiency Flag: Better alternatives exist for moment.
Added Size: 4.15MB
Cost Impact: $0.032/mo CI
Alternatives: dayjs, date-fns, luxon
💡 Fix: Run `npm uninstall moment && npm install dayjs`🔴 request
Health: 15/100
Verdict: BLOCK
Reasons: Deprecated. Maintainer explicitly marked as end-of-life.
Alternatives: got, axios, node-fetch, ky🟢 @babel/parser
Health: 94/100
Verdict: ALLOW ✨ PkgDiet Certified
Added Size: 1.77MBPkgDiet is a fully working MCP server. Any MCP-compatible agent (Claude, Cursor, Windsurf, Copilot, Cline, and others) can call it to vet packages mid-task — before writing an install command.
npx pkgdiet agent-setup --allAutomatically writes the correct MCP config to all detected agents simultaneously:
Claude Desktop → claude_desktop_config.json
Cursor → .cursor/mcp.json + .cursorrules
Windsurf → .windsurfrules
Cline → cline_mcp_settings.json
GitHub Copilot → .github/mcp.json
Claude Code → claude mcp add
Or configure a specific agent:
npx pkgdiet agent-setup --agent cursor
npx pkgdiet agent-setup --agent claude-desktop
npx pkgdiet agent-setup --detect # auto-detect from your project{
"mcpServers": {
"pkgdiet": {
"command": "npx",
"args": ["-y", "pkgdiet@2.0.0", "mcp"]
}
}
}Tip: Run
npx pkgdiet@2.0.0 mcponce in a terminal first to warm the npm cache. Subsequent agent launches will start in ~260ms.
Tool | What it does |
| ALLOW / WARN / BLOCK verdict for a single package |
| Batch verdict for multiple packages |
| Curated lighter/safer replacements |
| Active policy with validation status |
Recommended agent workflow:
Call check_dependency before recommending or installing any package.
If verdict is BLOCK → do not install without explicit user direction.
If verdict is WARN → explain the reasons and call suggest_alternative.
Re-check the chosen alternative with check_dependency.
Create .pkgdietrc.json in your project root (or run npx pkgdiet setup):
{
"minHealthScore": 70,
"securityMode": "standard",
"blockedPackages": ["request", "node-uuid", "colors"],
"internalNamePrefixes": ["@myorg/"],
"environments": {
"ci": {
"minHealthScore": 80,
"securityMode": "strict",
"failOn": "WARN"
}
}
}Validate your policy at any time:
npx pkgdiet policy-checkCommand | Purpose |
| Instant verdict for one or more packages |
| Full project audit — unused, unhealthy, bloated |
| Machine-readable JSON output for CI/scripts |
| Configure AI agent MCP integrations |
| Start the MCP server over stdio |
| PR gate — evaluate new dependencies in CI |
| Validate your |
| Interactive policy + agent setup wizard |
| Browse curated replacements |
| Detect silent health degradation in installed deps |
name: PkgDiet
on:
pull_request:
branches: [main]
permissions:
contents: read
jobs:
dependency-policy:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
with: { fetch-depth: 0 }
- run: npx pkgdiet@2.0.0 ci --base HEAD~1 --env ci--json){
"projectName": "my-app",
"directDeps": 12,
"filesScanned": 84,
"usedDependencies": ["react", "lodash"],
"unusedDependencies": ["left-pad"],
"unhealthyDependencies": [{ "name": "request", "healthScore": 15 }],
"sizeResults": { "totalNodeModules": "627 MB", "unusedSize": "41 MB" },
"sizeIssues": [{ "name": "typescript", "size": "22.5 MB" }],
"overallScore": 82,
"repoSafetyScore": 76
}Node.js 20 or later
npm, yarn, or pnpm project
Network access for registry health checks (can be disabled)
Does | Does not |
Applies your local dependency policy | Guarantee a package is free of vulnerabilities |
Reads selected npm registry metadata | Replace CVE / OSV vulnerability scanning |
Gives verdicts and alternatives to AI agents | Force any AI client to follow its recommendation |
Fails CI on configured thresholds | Perform a full source audit of every package |
Use PkgDiet alongside vulnerability scanning (e.g. npm audit, Snyk, Socket.dev), not instead of it.
When network checks are enabled, PkgDiet sends the package name to public npm registry endpoints. No account, no hosted backend, no telemetry sent to external servers. A local metrics file (.pkgdiet-metrics.json) is written to your project — add it to .gitignore.
MIT — see LICENSE.
Check a dependency (e.g. npm package) for health, risk, and cost before installing.
| Name | Required | Description | Default |
|---|---|---|---|
| package | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of disclosing behavior. The phrasing 'check ... before installing' implies a read-only, non-mutating operation, which is useful. However, it does not describe the output format, whether the check contacts a registry/network, auth requirements, or possible side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence with no filler. It front-loads the operation, states the resource, and enumerates what is checked. Every word contributes to the agent's understanding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple (one required string, no nested objects), and the description covers what it checks and when to use it. However, since there is no output schema, the description should say more about what the agent will receive back; 'health, risk, and cost' implies the result dimensions but not their shape or interpretation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema only declares 'package' as a required string with no description. The tool description adds meaning by identifying the value as a dependency such as an npm package. It does not, however, specify accepted formats (e.g. bare name vs. versioned specifier), so it only partially compensates for 0% schema description coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Check' and the resource 'a dependency', and it names the evaluation dimensions: health, risk, and cost. It also gives an example ('npm package') and a usage stage ('before installing'). It stops short of 5 because it does not explicitly contrast this tool with its siblings suggest_alternative and get_policy.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
'before installing' provides clear usage context: this is a pre-install evaluation tool. It does not, however, state when not to use it or explicitly point to suggest_alternative or get_policy as alternatives, so it misses the highest bar.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the active PkgDiet dependency policy for this repository.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations, so the description itself must convey behavior. 'Get' clearly signals a read-only retrieval, and the zero-parameter shape means there is no input-triggered side-effect risk. It does not disclose error or missing-policy behavior, but for a simple getter this is mostly sufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that immediately states the action, target, and scope. There is no filler, repetition, or unnecessary detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter, no-output-schema getter, the description is sufficiently complete: an agent can invoke it without further setup and can infer that the return value is the active policy. No additional prerequisites or edge cases are necessary to understand the call.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters and the schema description coverage is effectively 100%. The baseline for a zero-parameter tool is 4, and the description adds no conflicting or missing parameter information.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Get') and a clearly identified resource ('active PkgDiet dependency policy for this repository'). This is distinct from the sibling tools check_dependency and suggest_alternative, which imply different actions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies that this tool should be used when the active policy needs to be retrieved, and it scopes that to 'this repository.' However, it provides no explicit guidance about when to choose this tool over check_dependency or suggest_alternative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Suggest a lighter, healthier alternative for a package.
| Name | Required | Description | Default |
|---|---|---|---|
| package | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of disclosing behavior. It only states the action and gives no indication of side effects, whether this is read-only, or what the output looks like.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with the action and object front-loaded. The qualifiers 'lighter, healthier' add some vagueness but do not make the description bloated.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no annotations and no output schema, the description leaves the return format, input semantics, and behavioral context mostly unspecified. It is enough to guess the intent, but not sufficient for confident, correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description only references 'a package' without clarifying the expected format, allowed values, or examples. It minimally confirms that the package is the input, but does not meaningfully compensate for the missing schema documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Suggest') and names a clear target ('lighter, healthier alternative for a package'), so the tool's basic purpose is understandable. It does not explicitly differentiate from sibling tools, but the intent is not ambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no explicit guidance on when to use this tool versus alternatives like check_dependency or get_policy. The only usage signal is implied by the verb 'Suggest,' which is not enough for reliable tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.2.1check_dependencyget_policysuggest_alternativeScored across 3 tools
Each tool targets a distinct action: evaluating a dependency, suggesting an alternative, and retrieving policy. There is no overlap in purpose, so an agent can easily select the right tool.
All tool names follow a consistent verb_noun snake_case pattern (check_dependency, suggest_alternative, get_policy). The naming is predictable and uniform.
With only 3 tools, the set is tightly scoped to the domain of dependency health analysis. Each tool serves a clear, non-redundant purpose and fits within the ideal 3-15 tool range.
The tool surface covers checking, suggesting alternatives, and viewing policy, which supports a typical dependency-review workflow. A minor gap is the absence of any policy update or management tool, but this may be intentionally out of scope.
Packagephobia MCP — install-size analysis for npm packages
Provide AI-powered real-time analysis and intelligence on NPM packages, including security, depend…
Detect malicious or vulnerable npm packages: registry search, OSV.dev and GitHub advisory lookups
Package intelligence for AI agents across npm, PyPI, crates.io and deps.dev. No API keys.