About zotero_mcp
zotero_mcp provides a custom MCP server and client for connecting to Zotero and querying document content through MCP. It is intended for users bringing Zotero materials into an LLM workflow and requires configuration for both LLM and Zotero API credentials.
Key features
- 01Connect to a Zotero library
- 02Query document content through MCP
- 03Provide a custom server and client
- 04Configure LLM and Zotero credentials
Use cases
- 01Query content from documents uploaded to Zotero
- 02Connect Zotero to a custom MCP client
- 03Use a configured LLM for literature queries
MCP support
The project includes an MCP server and client. The server connects to Zotero so a client can query document content through MCP.
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
Support connecting Zotero via MCP with a custom server and client, without the need for tools like the Claude app or Cursor.
Environment configuration
conda create -n mcp python=3.12 -y
conda activate mcp
pip install -r requirements.txt
Run MCP
First, create a .env file and fill in the following variables. zotero_api_key needs to be obtained from the Zotero official website, and api_key is your LLM's API key:
zotero_api_key=''
api_key=""
First, create a .env file and fill in the following variables:
model=""
llm_api_base = ""
llm_api_key=""
zotero_api_key=''
library_id=''
model is the name of the LLM, llm_api_base is the URL of the LLM, and llm_api_key is the API Key for the LLM. The zotero_api_key can be created by visiting the Zotero, and your library_id is shown below:
Then start the server:
python ./server.py
Open a new terminal window and run the client:
python ./client.py
Here's the testing result:
Upload files in Zotero in advance:
Query document content via MCP:
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.