MCP.so
ログイン

MCP server for Zotero

@kujenga

基本情報

カテゴリ

その他

ライセンス

MIT

トランスポート

stdio

作者

kujenga

MCP server for Zotero について

Model Context Protocol (MCP) server for the Zotero API, in Python

MCP server for Zotero 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": {
    "zotero-mcp": {
      "command": "npx",
      "args": [
        "@modelcontextprotocol/inspector",
        "uv",
        "run",
        "zotero-mcp"
      ]
    }
  }
}

MCP server for Zotero 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。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is Model Context Protocol server for Zotero?

This project is a Python server that implements the Model Context Protocol (MCP) for Zotero, providing AI assistants with access to your Zotero library. It is designed for researchers and anyone who wants to interact with their personal Zotero collection through AI tools.

How to use Model Context Protocol server for Zotero?

Configure the server using environment variables (ZOTERO_LOCAL, ZOTERO_API_KEY, ZOTERO_LIBRARY_ID, ZOTERO_LIBRARY_TYPE) and run it via uvx (or pipx) with your MCP client, such as Claude Desktop. Alternatively, use the provided Docker image with the Zotero Web API. Enable the local Zotero API in the Zotero desktop settings for direct access.

Key features of Model Context Protocol server for Zotero

  • Search items in your Zotero library using text queries.
  • Get detailed metadata for specific Zotero items.
  • Retrieve full text (PDF contents) from Zotero items.
  • Supports both local Zotero API and Zotero Web API.
  • Works with any MCP client or the MCP Inspector.
  • Can be run via uvx, pipx, Docker, or local clone.

Use cases of Model Context Protocol server for Zotero

  • Ask an AI assistant to find and summarize references from your Zotero library.
  • Automatically extract metadata and full text for literature reviews.
  • Integrate Zotero citations into AI-generated reports or documents.
  • Quickly query your personal research collection through natural language.

よくある質問

1

What dependencies are required to run the server?

Python and `uvx` (or `pipx`) are needed; alternatively, Docker can be used. For the local API, Zotero desktop must be running with the local API enabled.

2

How does the server access my Zotero data?

It connects either via the local API (Zotero desktop app, no API key required) or through the Zotero Web API (requires an

コメント

「その他」の他のコンテンツ