About package-meta
package-meta is a stdio MCP server that provides package metadata, download counts, and maintainer health information for npm, PyPI, and Cargo packages. It is intended for agents that need package details.
Key features
- 01Retrieve npm package metadata
- 02Retrieve PyPI package metadata
- 03Retrieve Cargo package metadata
- 04Access download and maintainer health data
- 05Override remote snapshot or use local data
Use cases
- 01Inspect package details during dependency selection
- 02Check package downloads and maintainer health
- 03Use a local snapshot without remote fetching
MCP support
It runs as a stdio MCP server and makes package metadata, downloads, and maintainer health data available to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @weiseer/package-meta-mcpPKG_META_URLOverride remote snapshot URLPKG_META_LOCAL_ONLYSkip remote fetchLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
4Saved tool list · updated 3w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| name | string | Yes | |
| ecosystem | string | No | npm/pypi/cargo/maven/go |
Details
From the project README@weiseer/package-meta-mcp
npm/PyPI/Cargo package metadata + downloads + maintainer health. stdio MCP server.
Part of weiseer — AI-agent-native cached oracles.
Install
npm install -g @weiseer/package-meta-mcp
Use with Claude Desktop / Cursor / Cline / Continue / Windsurf
{
"mcpServers": {
"package-meta": {
"command": "npx",
"args": ["-y", "@weiseer/package-meta-mcp"]
}
}
}
Why use this instead of your agent doing it itself
The DIY cost in token-spend, latency, and rate-limit risk is 100-1500x our cost. See the weiseer organization README for the economic argument.
Environment
PKG_META_URL— override remote snapshot URLPKG_META_LOCAL_ONLY=1— skip remote fetch
License
Apache-2.0
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.