What is Npm Package Docs?
It’s an MCP server that retrieves the latest documentation for any npm package, fetching the README from the package’s GitHub repository or the npm package tarball.
@meanands
Basic information
A Model Context Protocol (MCP) server that provides up-to-date documentation for npm packages directly in your IDE. This tool fetches the latest README documentation from either the package's GitHub repository or the README bundled with the npm package itself.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"npm-package-docs-mcp": {
"command": "npx",
"args": [
"meanands/npm-package-docs-mcp"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
This MCP tool helps your IDE retrieve the most current README documentation for any npm package, fetching it from the package’s GitHub repository or the npm package tarball as a fallback.
Use the provided tool get_docs_for_npm_package with the packageName parameter (e.g., "react") through any MCP‑compatible client like Cursor.
It’s an MCP server that retrieves the latest documentation for any npm package, fetching the README from the package’s GitHub repository or the npm package tarball.
It first tries the package’s GitHub repository (checking `main`, `master`, or `develop` branches). If no GitHub repository is found, it downloads the npm package tarball and extracts the README.
It works with any IDE that supports the MCP protocol, such as Cursor.
Yes, the tool fetches the latest documentation in real‑time from the source, ensuring you always have the most current information.
Any npm package. Provide the package name as the `packageName` parameter (e.g., `"lodash"`).

Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.

Serve your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab
Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.

Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.

One permissioned folder your team and your AI agents both log into.
Comments