About Package Intel MCP
Package Intel MCP provides dependency metadata and supply-chain health data for AI agents evaluating npm, PyPI, and crates.io packages. It combines package registry details with deps.dev signals, without requiring API keys.
Key features
- 01Package metadata and versions
- 02Download counts and popularity
- 03Direct dependency lookup
- 04Health signals and Scorecard data
- 05Keyword package search
Use cases
- 01Check package health before adding a dependency
- 02Compare package release histories
- 03Review dependencies and maintenance signals
MCP support
Exposes tools for package search, metadata, versions, downloads, dependencies, and health to MCP clients over HTTP.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://package.datakoot.com/mcpclaude mcp add --transport http com-datakoot-npm-pypi-crates-packages https://package.datakoot.com/mcp{"mcpServers":{"com-datakoot-npm-pypi-crates-packages":{"type":"http","url":"https://package.datakoot.com/mcp"}}}Open in Cursor{"servers":{"com-datakoot-npm-pypi-crates-packages":{"type":"http","url":"https://package.datakoot.com/mcp"}}}Open in VS Code{"mcpServers":{"com-datakoot-npm-pypi-crates-packages":{"type":"http","url":"https://package.datakoot.com/mcp"}}}{"mcpServers":{"com-datakoot-npm-pypi-crates-packages":{"serverUrl":"https://package.datakoot.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
6| Parameter | Type | Required | Description |
|---|---|---|---|
| name | string | Yes | Package/crate name |
| ecosystem | enum | Yes | Package registry to look in. One of: npm, pypi, cargo.npm | pypi | cargo |
Details
From the project READMEPackage Intel MCP — by Datakoot
Software supply-chain intelligence for AI agents — as MCP tools your agent can call mid-task, so it can vet a dependency before it installs it. Covers npm, PyPI and crates.io. No API keys.
Tools
| Tool | What it does | Source |
|---|---|---|
package_info | Metadata for a package: description, latest version, license, homepage & repo links | npm / PyPI / crates.io |
package_versions | Full version history with release dates | npm / PyPI / crates.io |
package_downloads | Download counts and popularity signal | npm / PyPI / crates.io |
package_dependencies | Direct dependencies for a given version | deps.dev |
package_health | Health signals: OpenSSF Scorecard, stars, dependents | deps.dev |
package_search | Search for packages by keyword | npm / PyPI / crates.io |
Every tool accepts an ecosystem of npm, pypi, or crates. No API keys required.
Quick start
claude mcp add --transport http package-intel https://package.datakoot.com/mcp
Or point any MCP client at https://package.datakoot.com/mcp.
Try it in 10 seconds — no key, no signup
Paste this into a terminal:
curl -s https://package.datakoot.com/mcp \
-H 'content-type: application/json' \
-H 'accept: application/json, text/event-stream' \
-d '{"jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": {"name": "package_health", "arguments": {"ecosystem": "npm", "name": "express"}}}'
You get a supply-chain health snapshot for the npm package express — versions, downloads, dependencies, maintenance signals — no API key, nothing to sign up for.
Or point any MCP client at the URL and just ask your agent, in plain language:
- "How healthy is the npm package
express?" - "Before I add
left-pad, is it actively maintained and widely used?"
Data & attribution
Data comes from the public registry APIs for npm, PyPI and crates.io, plus deps.dev (Google Open Source Insights, CC-BY 4.0) for dependency graphs and OpenSSF Scorecard health signals. Package data is served from official public APIs and is informational.
Part of Datakoot — keyless intelligence APIs for AI agents.
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.