Advertise
MCP.so
Sign In
Z

Zotero MCP Server

@BirdInTheTree

Repository

Basic information

Category

Other

Transports

stdio

Author

BirdInTheTree

Submitted by

BirdInTheTree

About Zotero MCP Server

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

#zotero#bibliography#research#mcp#write

Zotero MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "zotero": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/zotero-mcp",
        "python",
        "-m",
        "zotero_mcp"
      ],
      "env": {
        "ZOTERO_LOCAL": "true"
      }
    }
  }
}

Zotero MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Zotero MCP?

Zotero MCP is a read+write MCP server with full write support for managing a Zotero library from AI assistants. It lets you create items, manage collections, find and merge duplicates, and import BibTeX from within Claude Code, Claude Desktop, or any MCP-compatible client. The server uses the Zotero Web API and requires a personal API key and user ID.

How to use Zotero MCP?

Install Python 3.11+ and uv, then clone the repo and run uv sync. Configure two environment variables: ZOTERO_API_KEY (get at https://www.zotero.org/settings/keys) and ZOTERO_USER_ID (shown on the same page). Add the server to your MCP client (e.g., Claude Code or Claude Desktop) by specifying the command uv run --directory /path/to/zotero-mcp python -m zotero_mcp and the required environment variables.

Key features of Zotero MCP

  • Full-text search with collection, type, and tag filters
  • Create items from field data or automatically from a DOI
  • Import BibTeX entries into a collection
  • Manage collections: create, add items, remove items
  • Find and merge duplicates with conflict protection
  • Update and delete items with version conflict protection

Use cases of Zotero MCP

  • Search your Zotero library for papers using natural language queries
  • Create new collections and organize items across them
  • Import BibTeX references into a specific collection
  • Find duplicate items in your library and merge them into one
  • Look up a DOI and automatically add the paper to your library

Frequently asked questions

1

What dependencies or runtime does Zotero MCP require?

Python 3.11+ and the `uv` package manager. All other dependencies are installed via `uv sync`.

2

What authentication is needed?

You must provide a Zotero Web API key and your Zotero user ID. These are set as environment variables `ZOTERO_API_KEY` and `ZOTERO_USER_ID`.

3

Where does my data live?

The server communicates with your Zotero library via the Zotero Web API. All data remains in your Zotero account; no additional storage is used.

4

Can I write to my Zotero library?

Yes, the server includes full write support: create items, update, delete, manage collections, and merge duplicates.

5

What transports or protocols does the server use?

The server uses the standard MCP protocol and can be used with any MCP-compatible client (e.g., Claude Code, Claude Desktop).

Comments

More Other MCP servers

P

PickFu MCP

PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

Awesome Mlops

visenger

A curated list of references for MLOps

14.0K

EverArt

modelcontextprotocol

Model Context Protocol Servers

88.1K

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K
Advertise