MCP server

Zotero MCP

MCP server published on pypi as zotero-mcp-server. Transports: stdio. Maintained in 54yyyu/zotero-mcp.

Website (opens in a new tab)Source (opens in a new tab)

Checked 2026-10-31

Install

Claude Code
claude mcp add zotero-mcp -- uvx zotero-mcp-server

Commands come from the project's own docs or registry entry. Check them against the source before you run them.

Loading poll...

Zotero MCP connects a Zotero research library to Claude and other assistants, so you can discuss papers, ask for summaries and analyse citations. The maintainer is 54yyyu, the install is uvx zotero-mcp-server over stdio, and the licence is MIT. The repository has 5.7 thousand stars and was last pushed on 16 October 2026. We would suggest it to students and researchers whose reading list already lives in Zotero, since the agent works from your own collection instead of the open web. The limits are the usual ones for summaries of papers: a model can misstate a result, so quote-check anything you cite. Whether it reads full text or only metadata depends on your setup, which the README explains, and we have not tested either route. It sits well beside an arXiv search server for finding new papers.

Mentioned here

Works with

Tried it with one of these? Vote below: works for me, or not.

Questions

How do I install Zotero MCP?

Run this command: claude mcp add zotero-mcp -- uvx zotero-mcp-server. The install box on this page has the command for each agent it works with.

Is Zotero MCP free?

It is published under the MIT licence.

Who maintains Zotero MCP?

It is maintained by 54yyyu. The code is at github.com/54yyyu/zotero-mcp.

What does Zotero MCP need to connect?

It runs over stdio.

Loading poll...

Reviews

Loading reviews…

Write a review

Your rating

Up to 1000 characters. Stars alone are enough.

Similar

  • browser-use MCP

    Browser Use is an open-source Python library for AI browser agents, and our entry covers its MCP route.

    • MCP server
    • Official

    browser-use · 119,597 stars

  • Scrapling MCP Server

    Scrapling is a Python web scraping framework from D4Vinci, described on GitHub as handling everything from a single request to a full-scale crawl, and this entry is its MCP server.

    • MCP server

    D4Vinci · 90,477 stars

  • Netdata MCP

    Netdata is an observability platform, and this entry is its hosted MCP endpoint at app.netdata.cloud, reached over streamable HTTP.

    • MCP server

    netdata · 81,227 stars

  • claude-flow MCP

    Claude Flow is published on npm as claude-flow, and its repository now sits at ruvnet/ruflo, which the GitHub description calls the original agent harness for deploying multi-agent swarms and coordinating autonomous workflows.

    • MCP server

    ruvnet · 80,298 stars

  • Context7 MCP

    Context7 is an MCP server from Upstash that serves up-to-date library documentation to coding agents, so the model reads current docs instead of guessing from training data.

    • MCP server

    upstash · 63,974 stars

  • Chrome DevTools MCP

    MCP server published on npm as chrome-devtools-mcp. Transports: stdio. Maintained in ChromeDevTools/chrome-devtools-mcp.

    • MCP server

    ChromeDevTools · 54,503 stars

Part of the Wbcom Designs family

The all-in-one WordPress community stack

Also ours: wbcomdesigns.comvapvarun.combrndle.com