広告掲載
MCP.so
ログイン

MCP Npm_docs Server

@bsmi021

リポジトリ

基本情報

カテゴリ

メモリとナレッジ

ライセンス

MIT

トランスポート

stdio

作者

bsmi021

MCP Npm_docs Server について

An MCP server that provides a tool to fetch metadata and documentation (including README content) for NPM packages, using a local cache to improve performance.

#npm#docs#npm-package#mpc#claude#modelcontextprotocol

MCP Npm_docs Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "mcp-npm_docs-server": {
      "command": "node",
      "args": [
        "dist/server.js"
      ]
    }
  }
}

MCP Npm_docs Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Mcp Npm_docs Server?

An MCP server that provides a tool to fetch metadata and documentation (including README content) for NPM packages. It uses the npms.io API and caches results locally with SQLite to improve performance. It is intended for developers using MCP clients (like Cline) who need programmatic access to package documentation.

How to use Mcp Npm_docs Server?

Install dependencies with npm install, build with npm run build, then run the compiled server with node dist/server.js. Configure caching via environment variables NPM_CACHE_TTL and NPM_CACHE_DB_PATH. Integrate with an MCP client by adding the server entry (using the absolute path to dist/server.js) to the client’s MCP settings file. The server exposes a single tool getNpmPackageDocs.

Key features of Mcp Npm_docs Server

  • Fetches package metadata and README via npms.io API.
  • Caches results locally using SQLite (better-sqlite3).
  • Provides the getNpmPackageDocs MCP tool.
  • Configurable cache TTL (default 24 hours).
  • Supports forceFresh parameter to bypass cache.
  • Follows standard MCP server structure.

Use cases of Mcp Npm_docs Server

  • Retrieve documentation and metadata for a specific NPM package.
  • Integrate package information into developer tools or workflows.
  • Reduce API calls and speed up repeated lookups using local caching.
  • Programmatically check package version, dependencies, license, and README.

よくある質問

1

What does the `getNpmPackageDocs` tool return?

It returns a JSON object with the package name, version, description, homepage, repository URL, author, license, keywords, dependencies, devDependencies, and README markdown content (when available via npms.io).

2

How can I bypass the cache for a fresh lookup?

Set the `forceFresh` parameter to `true` when calling the tool.

3

How do I configure the cache TTL?

Set the environment variable `NPM_CACHE_TTL` to a number of seconds. The default is 86400 (24 hours).

4

What API does the server use?

It uses the [npms.io API](https://api.npms.io/) to fetch package data. The `NPM_REGISTRY_URL` config variable exists but is currently ignored.

5

What are the runtime dependencies?

The server requires Node.js. It uses `better-sqlite3` for caching and is built with TypeScript. All dependencies are installed via `npm install`.

コメント

「メモリとナレッジ」の他のコンテンツ

Leviathan Systems Public Content MCP

Leviathan Systems

Search published GPU deployment, rack integration and structured cabling resources; read canonical documents and Leviathan Systems company service scope. Anonymous, read-only Streamable HTTP MCP. No credentials required.

Neither MCP

stonianua

Project context your AI can query through MCP — with source evidence.

AOCI-CODE

aoci-spec

Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.

1.7K

Tempreon

Tempreon

Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.

Groundwork

Rarefied-Earth

Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.

1
広告掲載