Package Intel MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Package Intel MCP ServerGet summary for lodash on npm"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Package Intel MCP Server
A Model Context Protocol (MCP) server for querying package registries (npm, PyPI, crates.io) to retrieve metadata about packages including versions, release cadence, and maintenance signals.
Features
Multi-Registry Support: Query npm, PyPI, and crates.io from a single interface
Package Summaries: Get comprehensive package metadata including version, license, and repository info
Release Timelines: Retrieve version history with release dates
Maintenance Signals: Analyze package health with automated scoring
Related MCP server: NPM Sentinel MCP
Installation
npm install
npm run buildUsage
As MCP Server (stdio)
npm startAs HTTP Server
npm run start:http
# Or with custom port
PORT=8080 npm run start:httpClaude Desktop Configuration
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"package-intel": {
"command": "node",
"args": ["/path/to/package-intel/dist/cli.js"]
}
}
}Tools
package_summary
Get summary information about a package.
Parameters:
ecosystem(required):"npm"|"pypi"|"crates"name(required): Package name
Example:
{
"ecosystem": "npm",
"name": "lodash"
}Response:
{
"ok": true,
"data": {
"name": "lodash",
"version": "4.17.21",
"description": "Lodash modular utilities.",
"homepage": "https://lodash.com/",
"repository": "https://github.com/lodash/lodash",
"license": "MIT",
"keywords": ["modules", "stdlib", "util"]
},
"meta": {
"source": "https://registry.npmjs.org/lodash",
"retrieved_at": "2024-01-15T10:30:00.000Z",
"pagination": { "next_cursor": null },
"warnings": []
}
}release_timeline
Get the release history of a package.
Parameters:
ecosystem(required):"npm"|"pypi"|"crates"name(required): Package namelimit(optional): Maximum releases to return (default: 20, max: 100)
Example:
{
"ecosystem": "pypi",
"name": "requests",
"limit": 5
}Response:
{
"ok": true,
"data": {
"package_name": "requests",
"ecosystem": "pypi",
"releases": [
{
"version": "2.31.0",
"date": "2023-05-22T10:00:00.000Z",
"is_prerelease": false
},
{
"version": "2.30.0",
"date": "2023-05-01T10:00:00.000Z",
"is_prerelease": false
}
],
"total_versions": 87
},
"meta": {
"source": "https://pypi.org/pypi/requests/json",
"retrieved_at": "2024-01-15T10:30:00.000Z",
"pagination": { "next_cursor": "5" },
"warnings": []
}
}maintenance_signals
Analyze maintenance health signals for a package.
Parameters:
ecosystem(required):"npm"|"pypi"|"crates"name(required): Package name
Example:
{
"ecosystem": "crates",
"name": "serde"
}Response:
{
"ok": true,
"data": {
"package_name": "serde",
"ecosystem": "crates",
"days_since_last_release": 45,
"last_release_date": "2023-12-01T10:00:00.000Z",
"releases_per_year": 12.5,
"total_versions": 156,
"is_deprecated": false,
"maintenance_score": "good",
"score_factors": {
"recency": "good",
"frequency": "good",
"maturity": "good"
}
},
"meta": {
"source": "https://crates.io/api/v1/crates/serde",
"retrieved_at": "2024-01-15T10:30:00.000Z",
"pagination": { "next_cursor": null },
"warnings": []
}
}Maintenance Score Calculation
The maintenance score is calculated based on three factors:
Recency (50% weight)
Good: Last release < 90 days ago
Fair: Last release < 365 days ago
Poor: Last release >= 365 days ago
Frequency (30% weight)
Good: >= 4 releases per year
Fair: >= 1 release per year
Poor: < 1 release per year
Maturity (20% weight)
Good: >= 10 total versions
Fair: >= 3 total versions
Poor: < 3 total versions
If a package is deprecated, the score is automatically set to "poor".
Error Handling
All tools return errors in a consistent envelope format:
{
"ok": false,
"error": {
"code": "INVALID_INPUT",
"message": "Package 'nonexistent' not found on npm",
"details": {
"package": "nonexistent",
"ecosystem": "npm"
}
},
"meta": {
"retrieved_at": "2024-01-15T10:30:00.000Z"
}
}Error Codes
INVALID_INPUT: Invalid parameters or package not foundUPSTREAM_ERROR: Registry API returned an unexpected errorRATE_LIMITED: Registry rate limit exceededTIMEOUT: Request timed outPARSE_ERROR: Failed to parse registry responseINTERNAL_ERROR: Unexpected server error
Configuration
Environment variables (see .env.example):
Variable | Default | Description |
|
| HTTP server port |
|
| Request timeout in ms |
|
| User agent for registry requests |
|
| Cache TTL in seconds |
|
| Log level: debug, info, warn, error |
Development
# Install dependencies
npm install
# Build
npm run build
# Run tests
npm test
# Run tests in watch mode
npm run test:watch
# Type check
npm run typecheck
# Development mode (watch)
npm run devLicense
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/BUZDOLAPCI/package-intel'
If you have feedback or need assistance with the MCP directory API, please join our Discord server