About Zotero MCP Server
Zotero MCP Server exposes a local Zotero library to MCP clients, for researchers who need to search papers and manage notes. It can connect through the Zotero API or access the SQLite database directly.
Key features
- 01Search papers by tag
- 02Read paper details and notes
- 03Add notes to papers
- 04Request paper summaries
- 05Access data directly through SQLite
Use cases
- 01Find research papers by tag
- 02Review paper details and notes
- 03Record notes on paper entries
MCP support
This MCP server lets MCP clients access a local Zotero library, with capabilities for paper search, detail lookup, note management, and summary requests.
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 MCP (Model Context Protocol) server to let your MCP clients (e.g. Anthropic Claude App, Goose, possibly vscode Cline too) interact with your local Zotero repository. This server enables programmatic access to your Zotero library, allowing you to search papers, manage notes, and more.
Note: If you don't want to set up API keys, see the SQLite database server option below.
Setup
- Install dependencies:
pip install -e .
- Create a
.envfile in the root directory with your Zotero credentials:
ZOTERO_API_KEY=your_api_key_here
ZOTERO_USER_ID=your_user_id_here
You can get your Zotero API key and user ID from Zotero's settings page.
Integration with Anthropic Desktop App
To integrate with the Anthropic Desktop app, add the following configuration to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"zotero-mcp-server": {
"command": "uv",
"args": [
"--directory",
"/Users/swairshah/work/research/zotero-mcp",
"run",
"python",
"-m",
"zotero_mcp.server"
]
}
}
}
If this gives an error like
{"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"claude-ai","version":"0.1.0"}},"jsonrpc":"2.0","id":0}
error: unexpected argument '--directory' found
Then use the following config, make sure to do uv venv; source .venv/bin/activate; uv pip install ".[dev]" to make sure the server can be run with all dependencies.
{
"mcpServers": {
"zotero-mcp-server": {
"command": "bash",
"args": [
"-c",
"cd /Users/shahswai/personal/zotero-mcp-server && source .venv/bin/activate && python -m zotero_mcp.server"
]
}
}
}
Alternative: Direct SQLite Database Access
If you prefer to bypass the Zotero API entirely and work directly with the SQLite database, use zotero_mcp/db_server.py. This approach gives you full control over your Zotero data without API limitations. Note that you'll need to close Zotero completely before using this method since SQLite locks the database when Zotero is running.
Claude MCP config for the SQLite version:
{
"mcpServers": {
"zotero-mcp-server": {
"command": "uv",
"args": [
"--directory",
"/Users/swair/work/code/zotero-mcp-server",
"run",
"python",
"-m",
"zotero_mcp.db_server"
]
}
}
}
Example Usage

The server allows you to:
- Search papers by tags
- Get paper details and attached notes
- Add notes to papers
- Request paper summaries
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.