The Zotero MCP server acts as a bridge between personal research libraries and AI assistants. In simple terms, it allows an AI like Claude to "look into" a user's Zotero collection to find specific academic papers, books, or articles. Instead of a user having to manually copy and paste citation info or PDF text into a chat window, this tool lets the AI browse, search, and read the contents of a library directly to help with drafting bibliographies or summarizing complex research. Under the hood, this Python-based server provides three primary tools that AI agents can use sequentially to complete sophisticated tasks. The `zotero_search_items` tool identifies relevant entries via text queries, while `zotero_item_metadata` pulls detailed bibliographic data for precise referencing. Most impressively, the `zotero_item_fulltext` tool allows the AI to extract the actual text content from stored PDFs, enabling deep analysis of document contents. This functionality can be powered either by the Zotero Web API for cloud-based access or a local API for those who prefer the speed and privacy of the desktop application. For developers and researchers building custom AI workflows, this server is highly flexible and easy to deploy. It supports multiple installation methods, including Docker containers for isolated environments and `uvx` for quick local execution. By standardizing Zotero interactions through the Model Context Protocol, it eliminates the need for developers to write custom scraping or API-handling code for every research project. This makes it an essential utility for anyone wanting to give their LLM-powered applications a "scholarly memory" capable of synthesizing vast amounts of academic data with minimal friction.

1. Installation

The Zotero MCP server can be installed and run using uvx (via the uv package manager) or Docker. You must first choose between the Local API or the Web API.

Prerequisites:

• Local API (Faster):
  1. Open Zotero and go to Settings > Advanced.
  2. Check "Allow other applications on this computer to communicate with Zotero".
  3. Note: To access full-text PDF content via the local API, you currently need the Zotero Beta Build.
• Web API:
  1. Create an API key and find your Library ID (User ID) at zotero.org/settings/keys.

2. Configuration

Add the following to your claude_desktop_config.json (or equivalent MCP settings file for Cursor/Cline):

Option A: Using uvx (Local API)

{
  "mcpServers": {
    "zotero": {
      "command": "uvx",
      "args": ["--upgrade", "zotero-mcp"],
      "env": {
        "ZOTERO_LOCAL": "true",
        "ZOTERO_API_KEY": "",
        "ZOTERO_LIBRARY_ID": ""
      }
    }
  }
}

Option B: Using Docker (Web API)

Replace PLACEHOLDER with your actual Zotero API key and User ID.

{
  "mcpServers": {
    "zotero": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e", "ZOTERO_API_KEY=PLACEHOLDER",
        "-e", "ZOTERO_LIBRARY_ID=PLACEHOLDER",
        "ghcr.io/kujenga/zotero-mcp:main"
      ]
    }
  }
}

Environment Variables Reference:

• ZOTERO_LOCAL: Set to true for local app access, false for web API.
• ZOTERO_API_KEY: Required for Web API.
• ZOTERO_LIBRARY_ID: Required for Web API.
• ZOTERO_LIBRARY_TYPE: Set to user (default) or group.

3. Available Tools

• zotero_search_items: Search for items in your Zotero library using a text query.
• zotero_item_metadata: Get detailed metadata (author, date, tags, etc.) about a specific Zotero item.
• zotero_item_fulltext: Get the full text content of a specific Zotero item (e.g., PDF contents).

4. Example Prompts

• "Search my Zotero library for papers about 'Transformer architectures' and give me a summary of the most recent one."
• "Retrieve the full text of my Zotero item titled 'Attention is All You Need' and explain its main conclusion."
• "Look up the metadata for my recent Zotero additions and list the authors for each."

Use Case 1: Automated Literature Review and Synthesis

Problem: Researchers often accumulate dozens of PDFs in their Zotero library and struggle to quickly synthesize findings or compare methodologies across multiple papers without manually re-reading every document.
Solution: This MCP allows an AI assistant to act as a research partner. It can search for specific keywords across the library, pull the full text of relevant papers, and provide a comparative summary or a thematic analysis of the research.
Example: A user asks, "Find all papers in my library about 'transformer architectures' from 2023 and summarize their different approaches to attention mechanisms." The AI uses zotero_search_items to find the papers, zotero_item_fulltext to read the PDFs, and generates a structured report.

Use Case 2: Accurate Bibliographic Management and Formatting

Problem: When writing a manuscript, users often remember a concept but forget the exact publication year, co-authors, or journal name required for a citation, leading to manual searching within the Zotero desktop app.
Solution: The AI can instantly retrieve precise metadata for any item in the library. Because the AI has access to the raw metadata via zotero_item_metadata, it can format citations in any style (APA, BibTeX, Chicago) or verify if a citation in a draft is accurate.
Example: A user says, "I'm writing a paper and need the BibTeX entry for the paper by Smith about neural radiance fields." The AI searches for the item, retrieves its metadata, and outputs the perfectly formatted BibTeX code.

Use Case 3: Fact-Checking and Deep Content Querying

Problem: Researchers often remember that a paper contained a specific statistic or a niche experimental result but cannot remember which specific paper it was in or on which page it appeared.
Solution: Using the zotero_item_fulltext tool, the AI can "read" through the user's library to find specific mentions of data points or evidence that match a natural language query.
Example: A user asks, "Which paper in my library mentioned a 15% increase in efficiency using the 'Green-Algorithm'?" The AI searches for likely candidates, checks their full text, and replies: "That was 'Sustainable AI' by Jones et al. (2022), located in the Results section on page 4."

Use Case 4: Discovery of Research Gaps

Problem: It is difficult for a human to see the "big picture" of what is missing from their current collection of research when preparing a thesis or a new study.
Solution: By analyzing the metadata and full text of an entire Zotero collection, an AI can identify common trends and, more importantly, highlight topics that are underrepresented or conflicting in the user's current library.
Example: A user asks, "Based on my 'Climate Change' folder in Zotero, what are the most common arguments against the current models, and what perspectives am I missing?" The AI analyzes the metadata and content to suggest that the user has many papers on "atmospheric impact" but lacks "oceanic carbon sequestration" sources.