About Zotero MCP Server
Zotero MCP Server lets MCP-compatible AI applications access and manage personal or group Zotero libraries. It provides search, citation and bibliography functions, along with tools for editing library items and collections.
Key features
- 01Search library items
- 02Create citations and bibliographies
- 03Add and update library items
- 04Manage collections
- 05Access personal and group libraries
Use cases
- 01Find references in a Zotero library
- 02Generate a citation or bibliography
- 03Add or edit references and collections
MCP support
Exposes Zotero library resources and tools to MCP clients, including item search, citation generation, and library editing.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEZotero MCP Server
A Model Context Protocol (MCP) server that integrates with Zotero, allowing AI applications to access and manipulate Zotero libraries.
Built with the official MCP Python SDK following the latest MCP paradigms and best practices.
Features
- Search for items in Zotero libraries
- Get citations and bibliographies
- Add new items to Zotero libraries
- Access collections and items
- Support for both personal and group libraries
Installation
-
Clone the repository:
git clone https://github.com/your-username/zotero-mcp-server.git cd zotero-mcp-server -
Create a virtual environment:
python -m venv venv -
Activate the virtual environment:
- On Linux/macOS:
source venv/bin/activate - On Windows:
venv\Scripts\activate
- On Linux/macOS:
-
Install dependencies:
pip install -r requirements.txt
Configuration
-
Copy the example environment file:
cp .env.example .env -
Edit the
.envfile with your Zotero API credentials:ZOTERO_API_KEY=your_api_key_here ZOTERO_USER_ID=your_numeric_user_id_here # ZOTERO_GROUP_ID=your_group_id_here # Uncomment to use a group libraryYou need to set either
ZOTERO_USER_ID(for personal libraries) orZOTERO_GROUP_ID(for group libraries). -
If you're not sure how to find your Zotero user ID, run:
./find_zotero_id.py
Usage
Running the Server
python src/server.py
The server will start and listen for JSON-RPC requests on standard input/output.
Testing the Server
./simple_test.py
This will run a series of tests to verify that the server is working correctly.
Integration with AI Applications
The Zotero MCP server can be integrated with AI applications that support the Model Context Protocol. See the USAGE_GUIDE.md file for detailed examples.
Available Resources
zotero://collections: List of collections in the Zotero libraryzotero://items/top: Top-level items in the Zotero libraryzotero://items/recent: Recently added or modified items in the Zotero libraryzotero://collections/{collection_key}/items: Items in a specific Zotero collectionzotero://items/{item_key}: Details of a specific Zotero itemzotero://items/{item_key}/citation/{style}: Citation for a specific Zotero item in a specific style
Available Tools
search_items: Search for items in the Zotero libraryget_citation: Get citation for a specific itemadd_item: Add a new item to the Zotero libraryget_bibliography: Get bibliography for multiple itemscreate_collection: Create a new collection in the Zotero libraryupdate_item: Update an existing item in the Zotero librarydelete_item: Delete an item from the Zotero libraryget_item_types: Get list of all available Zotero item typesget_item_fields: Get available fields for a specific item type
Documentation
For more detailed information, see:
USAGE_GUIDE.md: Comprehensive usage guidetest_client.py: Interactive test clientsimple_test.py: Simple test scriptfind_zotero_id.py: Helper script to find your Zotero IDs
License
MIT
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.