cookjohn/zotero-mcp

It's a plugin extension in Zotero. Zotero MCP Plugin enables integration between AI assistants and Zotero through MCP. Zotero MCP Plugin 是一个 Zotero 插件，通过 MCP协议实现 AI 助手与 Zotero深度集成。插件支持文献检索、元 数据管理、全文分析和智能问答等功能，让 Claude、ChatGPT 等 AI 工具能够直接访问和操作您的文献库。

What it solves

Zotero MCP bridges the gap between AI assistants (such as Claude Desktop, Cursor, or Cherry Studio) and Zotero reference management software. It allows AI models to directly access, search, and manage a user's local academic library, eliminating the need to manually copy-paste references or PDF text into an AI prompt for literature reviews and research analysis.

How it works

The project provides a Zotero plugin with an integrated MCP (Model Context Protocol) server. This server uses a Streamable HTTP protocol to create a real-time bidirectional communication channel between the AI client and the local Zotero instance. Once configured, the AI assistant can call a suite of 29 specialized tools to perform actions within Zotero, such as extracting PDF text, searching for annotations, or updating metadata.

Who it’s for

Academic researchers, students, and knowledge workers who use Zotero to manage their citations and want to leverage LLMs to analyze their literature, automate citation management, and organize their research notes.

Highlights

  • Deep Library Integration: Supports multi-dimensional search (title, creator, year, tags) and full-text database access.
  • Content Extraction: Extracts full-text PDFs, notes, abstracts, and webpage snapshots with adjustable detail levels.
  • Semantic Search: Uses embedding vectors (via OpenAI or Ollama) to find conceptually related literature regardless of exact keyword matches.
  • Annotation Analysis: Ability to search and retrieve PDF highlights and annotations filtered by color or tags.
  • Write Capabilities: Allows AI assistants to create notes, manage tags, update metadata, and import new items via identifiers like DOI or arXiv.
  • Privacy-Focused: Operates locally to ensure data privacy.

Related

  • Project
    54yyyu/zotero-mcp

    Zotero MCP is an integration tool that connects your Zotero research library to AI agents and chat interfaces, allowing them to search, read, and annotate your academic papers.

  • Project
    docsagent/docsagent

    An MCP server that gives AI agents private, local access to search and read Zotero, Obsidian, and Apple Notes using a high-performance C++ search engine.

  • Project
    yilewang/llm-for-zotero

    llm‑for‑zotero is a Zotero add‑on that embeds a chat powered by any LLM (OpenAI‑compatible, Claude, Codex, etc.). It lets you ask questions about PDFs, get grounded citations, compare papers, save notes to Zotero or external Markdown folders, and (in beta Agent Mode) perform library‑wide actions like tagging, importing, and web search. Install via a .xpi file, configure a provider in Zotero’s preferences, and start chatting from the PDF reader.

  • Project
    steven-jianhao-li/zotero-AI-Butler

    Zotero‑AI‑Butler is an open‑source Zotero plug‑in that lets you call LLMs (Gemini, OpenAI, Claude, etc.) to automatically read PDFs, generate Markdown summaries, mind‑maps, one‑page visual abstracts, and batch literature‑review drafts. It works via a task queue, supports multi‑round prompting, Base64 PDF upload for multimodal models, and offers a sidebar preview with LaTeX rendering. Users supply their own API keys; the plug‑in stores no data. Installation is a simple .xpi download, and the UI provides right‑click shortcuts, a dashboard, and customizable prompt templates.

  • Project
    blazickjp/arxiv-mcp-server

    A local MCP server for agent literature work. The differentiator is original-LaTeX section reads, BibTeX from arXiv metadata, and topic watches. Papers stay on disk. The working loop is paper ID → outline → one section → citations. Search is optional.