Zotero

by kujenga

42 stars
5.1k downloads
Not rated
GitHub

About

Integrates with Zotero to enable searching libraries, retrieving metadata, and accessing full-text content for scholarly research workflows.

Details

Author
kujenga
Repository
kujenga/zotero-mcp
GitHub stars
42
Downloads
5,066
License
MIT License
Categories
Productivity, Other, Knowledge Base, Developer Tools, Design, AI, Search, Infrastructure, Security
Tags
#integration

Jump to

- 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.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Zotero
    Command (node, npx, python, etc.) uvx
    Arguments
    • Argument 1 zotero-mcp@latest
    Environment
    • ZOTERO_LOCAL true
    • ZOTERO_API_KEY
    • ZOTERO_LIBRARY_ID

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

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.

zotero_search_items

Search for items in your Zotero library using a text query.

zotero_item_metadata

Get the complete metadata for a specific Zotero item, covering every populated field grouped into publication details, identifiers, timestamps, and library information.

zotero_item_fulltext

Get the full text of a specific Zotero item (i.e. PDF contents).

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

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

Linux

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

Macos

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

Windows

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

Model Context Protocol server for Zotero

This project is a python server that implements theModel Context Protocol (MCP)forZotero, giving you access to your Zotero library within AI assistants. It is intended to implement a small but maximally useful set of interactions with Zotero for use withMCP clients.

This MCP server provides the following tools:

- zotero_search_items: Search for items in your Zotero library using a text query
- zotero_item_metadata: Get the complete metadata for a specific Zotero item, covering every populated field grouped into publication details, identifiers, timestamps, and library information
- zotero_item_fulltext: Get the full text of a specific Zotero item (i.e. PDF contents)

These can be discovered and accessed through any MCP client or through theMCP Inspector.

Each tool returns formatted text containing relevant information from your Zotero items, and AI assistants such as Claude can use them sequentially, searching for items then retrieving their metadata or text content.

This server can either run against either alocal API offered by the Zotero desktop application) or through theZotero Web API. The local API can be a bit more responsive, but requires that the Zotero app be running on the same computer with the API enabled. To enable the local API, do the following steps:
- Open Zotero and open "Zotero Settings"
- Under the "Advanced" tab, check the box that says "Allow other applications on this computer to communicate with Zotero".

To use the Zotero Web API, you'll need to create an API key and find your Library ID (usually your User ID) in your Zotero account settings here:https://www.zotero.org/settings/keys

These are the available configuration options:

- ZOTERO_LOCAL=true: Use the local Zotero API (default: false, see note below)
- ZOTERO_API_KEY: Your Zotero API key (not required for the local API)
- ZOTERO_LIBRARY_ID: Your Zotero library ID (your user ID for user libraries, not required for the local API)
- ZOTERO_LIBRARY_TYPE: The type of library (user or group, default: user)

To use this with Claude Desktop and a direct python install withuvx, add the following to themcpServersconfiguration:

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

The@latestspecifier is optional and will pull the latest version when new ones are available. If you don't haveuvxinstalled you can usepipx runinstead, or clone this repository locally and use the instructions inDevelopmentbelow.

If you want to run this MCP server in a Docker container, you can use the following configuration, inserting your API key and library 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" ], } } }

To update to a newer version, rundocker pull ghcr.io/kujenga/zotero-mcp:main. It is also possible to use the docker-based installation to talk to the local Zotero API, but you'll need to modify the above command to ensure that there is network connectivity to the Zotero application's local API interface.

Information on making changes and contributing to the project.
- Clone this repository
- Install dependencies withuvby running:uv sync
- Create a.envfile in the project root with the environment variables above

Start theMCP Inspectorfor local development:

npx @modelcontextprotocol/inspector uv run zotero-mcp

To test the local repository against Claude Desktop, runecho $PWD/.venv/bin/zotero-mcpin your shell within this directory, then set the following within your Claude Desktop configuration

{ "mcpServers": { "zotero": { "command": "/path/to/zotero-mcp/.venv/bin/zotero-mcp" "env": { // Whatever configuration is desired. } } } }

- Bump the version inpyproject.tomlandserver.json(two places: the server version and the package version).
- Publish to PyPI withmake publish.
- Publish updated metadata to theofficial MCP registrywithmake publish-mcp, authenticating first withmcp-publisher login githubif needed.

Build the container image with this command:

To test the container with the MCP inspector, run the following command:

npx @modelcontextprotocol/inspector \ -e ZOTERO_API_KEY=$ZOTERO_API_KEY \ -e ZOTERO_LIBRARY_ID=$ZOTERO_LIBRARY_ID \ docker run --rm -i \ --env ZOTERO_API_KEY \ --env ZOTERO_LIBRARY_ID \ zotero-mcp:local

- https://modelcontextprotocol.io/tutorials/building-mcp-with-llms
- https://github.com/modelcontextprotocol/python-sdk
- https://pyzotero.readthedocs.io/en/latest/
- https://www.zotero.org/support/dev/web_api/v3/start
- https://modelcontextprotocol.io/llms-full.txtcan be utilized by LLMs

Item metadata is rendered from whatever fields the API returns rather than from a fixed list. Fields it omits are skipped, and fields this server doesn't know about appear under an "Other Fields" heading, so a Zotero upgrade never silently drops metadata.

The two APIs differ in one way worth knowing: the local API's quick search indexes citation keys, while the Web API does not, so searching for one returns nothing over the Web API even though the field is present in the data.

Search, cite, and read PDFs from your EndNote reference library directly in Claude Desktop

Use a Zotero plugin-hosted MCP endpoint to let local agents manage a local Zotero library safely.

Read+write MCP server for Zotero with full write support — create items, manage collections, find and merge duplicates, import BibTeX

Official Notion MCP server for searching, reading, creating, and updating Notion pages, databases, and workspace content from AI agents.

MCP server for Apple Notes with semantic search and CRUD operations. Claude searches, reads, creates, updates, and manages your Apple Notes through natural language.

Markdown-first Notion MCP server with 9 composite tools, 39 actions, and ~77% token reduction via tiered docs.

AI-powered reading triage MCP. 26 tools with a 24h burn timer. Read less, absorb more.

Personal Knowledge Base MCP — 22 tools for AI agents to access your curated reading intelligence.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

Install

Add to Claude Desktop or Cursor

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

More like this

Similar MCP servers you might find useful

Browse category

Sequential Thinking

Sequential Thinking is an MCP server that provides a tool for dynamic and reflective problem-solving through a structured, step-by-step thinking process. It is…

88.2k
Other

Time

A Model Context Protocol server that provides time and timezone conversion capabilities. It enables LLMs to get current time information and perform timezone…

88.2k
Productivity

Memory

Memory is an MCP server that provides persistent memory using a local knowledge graph. It lets AI assistants like Claude remember information about the user…

88.1k
Knowledge Base

Filesystem

Filesystem is a Node.js server that implements the Model Context Protocol (MCP) for filesystem operations. It enables AI assistants to read, write, and manage…

88.1k
Other