package-intel-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| package_infoA | Get core metadata for a package: latest version, description, license, homepage, source repository, maintainers, and whether it is deprecated. Use before an agent installs or recommends a dependency. Ecosystems: npm, pypi, cargo. |
| package_versionsA | List recent released versions of a package with release dates (most recent first). Helps an agent pick a version or check how actively it is maintained. Ecosystems: npm, pypi, cargo. |
| package_downloadsA | Get popularity/download statistics for a package (recent download counts). Useful for judging how widely used and battle-tested a dependency is. Ecosystems: npm, pypi, cargo. |
| package_dependenciesA | List the direct dependencies of a specific package version (defaults to latest), via deps.dev. Lets an agent understand what a package pulls in before adding it. Ecosystems: npm, pypi, cargo. |
| package_healthA | A composite trust/health check for a package an agent is considering: latest-release recency, deprecation status, license present, maintainer count, dependency count, and any known security advisories (via deps.dev). Returns a summary an agent can act on. Ecosystems: npm, pypi, cargo. |
| package_searchA | Search for packages by keyword and get the top matches with descriptions. Supported ecosystems: npm and cargo (PyPI has no public search API). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool targets a distinct aspect of package intelligence (downloads, metadata, versions, dependencies, health, search), so selection is generally clear. There is mild overlap between package_info and package_health, since health reports a superset of info fields like license and deprecation, but the composite/actionable framing of health distinguishes it.
All six tools use a uniform package_<noun> snake_case pattern (package_info, package_versions, package_dependencies, etc.), making names highly predictable. No mixing of conventions or verb styles.
Six tools is well-scoped for a package-intelligence server, with each tool earning its place across popularity, metadata, versions, dependencies, health, and search. Nothing feels redundant or missing in size.
The surface covers a full evaluation lifecycle: discover (search), inspect (info, versions), assess risk (downloads, dependencies, health). Minor gap: package_search only works for npm and cargo, and there is no reverse-dependency or license-compatibility operation, but core workflows are covered.