Zotero MCP: A practical bridge between your research library and AI assistants
Zotero MCP: Connects your Zotero research library with Claude and other AI assistants via the Model Context Protocol to discuss papers, get summaries, analyze citations, and more.
At a glance
- What is it?
- Zotero MCP connects Zotero libraries to Claude, ChatGPT, and other MCP clients, offering search, annotations, write operations, and optional semantic search. The project also ships a standalone CLI and an agent skill that cuts context cost dramatically.
- Who is it for?
- Adopt Zotero MCP if you live in Zotero and want an AI assistant to read, summarize, or edit your library without manual export. It is a good fit for researchers who already use Claude Desktop, ChatGPT, or a shell-based agent like Claude Code.
- Can I use it commercially?
- Yes. MIT is a permissive licence: you can use, modify and sell software built on it, as long as you keep its copyright and licence notices.
- Is it still maintained?
- Yes. The repository last received commits 1 day ago.
- What is it written in?
- Mainly Python, according to GitHub's language statistics.
Answers come from the project's GitHub data, last synced on November 15, 2026, and from our analysis. They are not legal advice.
Star history
- 54yyyu/zotero-mcp5,925 ★ · +1,467
| Repository | 2026-07-28 | 2026-11-15 |
|---|---|---|
| 54yyyu/zotero-mcp | 4.5k | 5.9k |
1,467 Stars in the last 110 days, measured from the daily GitHub snapshot. Compare with other projects
Editorial analysis
What problem it solves and who it is for
Researchers and students accumulate large Zotero libraries, but getting an AI assistant to actually read those papers is awkward. You can copy text into a chat window, but that loses structure and context. Zotero MCP solves this by exposing your library as a set of tools that an MCP-compatible assistant can call directly. The target user is someone who already uses Zotero and wants to discuss papers, get summaries, or analyze citations without leaving their AI client. The README lists ChatGPT, Claude, Cherry Studio, Chorus, and Cursor as supported clients. If you are a Zotero power user who also writes with AI tools, this project removes a real friction point.
How the MCP server works under the hood
The server speaks the Model Context Protocol, which is a standardized way for AI assistants to call external tools. Those tools cover search by title, author, or content; browsing collections and tags; retrieving metadata in markdown or BibTeX; extracting PDF annotations; and write operations like adding papers by DOI or URL. The data flow is straightforward: the assistant sends a tool call, the server queries your Zotero library (local or web API), and returns structured results. The server also supports a hybrid mode where reads come from the local Zotero database and writes go through the web API. That design matters because local mode works offline but may not support all write operations, while web mode requires an API key.
Getting it running: install commands and configuration
Installation is straightforward if you have Python. The README recommends uv, but pip works too. The core command is `uv tool install zotero-mcp-server`, followed by `zotero-mcp setup` to auto-configure for Claude Desktop. The base install is lightweight, with no ML dependencies. Heavy features are gated behind extras: `semantic` for vector search via ChromaDB and sentence-transformers, `pdf` for PDF outline extraction with PyMuPDF, and `scite` for citation tallies and retraction alerts. You can install everything with `pip install "zotero-mcp-server[all]"`. Updating is handled by `zotero-mcp update`. The setup command also configures semantic search through `zotero-mcp setup --semantic-config-only`, according to .env.example.
The agent skill: a cheaper alternative for shell-capable clients
One of the more interesting design choices is the agent skill. The README's comparison table puts the skill, installed via `zotero-mcp install-skill`, at 98 tokens in context until it is needed, instead of ~17k for the MCP server. The skill teaches the agent to drive the standalone CLI (`zotero-cli`) directly. This is a clever workaround for clients that have shell access, like Claude Code or Cursor. If the skill produces wrong answers, the token savings are meaningless.
Semantic search and the optional extras trade-off
Semantic search is the headline feature for finding papers by concept rather than keyword. It uses ChromaDB for vector storage and supports multiple embedding models: local, OpenAI, Gemini, and Ollama embeddings. But this comes at a cost. The `semantic` extra pulls in sentence-transformers and other ML dependencies, which makes the install heavier. The README explicitly separates these extras so the base install stays fast. If you only need basic lookup and annotation, you do not need semantic search at all. The trade-off is real: semantic search gives better recall for vague queries, but it requires more setup and ongoing maintenance of the embedding index. For a small library, keyword search might be enough.
Scite integration: citation intelligence without an account
The `scite` extra adds citation tallies and retraction alerts. According to the README, no Scite account is needed. That is a notable advantage because Scite normally requires a subscription. For each item, you can see how many papers support, contrast, or mention it. Retraction alerts flag papers that have been retracted. This is useful for literature reviews where you need to know if a cited paper has been withdrawn. The limitation is that it depends on Scite's public data, which may not be as complete as the paid API. If you need deep citation graphs or citation networks, this extra might not be enough.
Write operations and the hybrid mode caveat
Zotero MCP is not read-only. You can add papers by DOI, URL, ISBN, BibTeX, or file (with open-access PDFs), manage collections and tags, and merge duplicates. These write operations are powerful, but they come with a caveat. Local mode reads straight from zotero.sqlite; on Zotero 10+, writes go to the running Zotero after you run `zotero-mcp authorize-local` once, while older Zotero versions write through the web API with ZOTERO_API_KEY and ZOTERO_LIBRARY_ID. A hybrid mode reads locally and writes via the web API.
Maintenance, licensing, and when it is the wrong tool
The repository is listed as MIT, but pyproject.toml declares the package licence as MIT AND AGPL-3.0-or-later, with license files LICENSE and plugin/LICENSE, so check both for exact terms. Maintenance appears active, with recent releases v0.15.0, v0.15.1 and v0.15.2 published between 2026-10-15 and 2026-11-01. However, the project is young and evolving quickly, so breaking changes between minor versions are possible. It is the wrong tool if you do not use Zotero regularly, or if your AI client does not support MCP and you do not want to install a CLI skill. It is also wrong if you need citation intelligence beyond what the Scite extra provides. For those cases, you might be better off exporting a BibTeX file and pasting it into a chat, or using a dedicated reference manager with built-in AI features.
Editorial conclusion
Adopt Zotero MCP if you live in Zotero and want an AI assistant to read, summarize, or edit your library without manual export. It is a good fit for researchers who already use Claude Desktop, ChatGPT, or a shell-based agent like Claude Code. Skip it if you rarely touch Zotero or if you need deep citation analytics beyond Scite's citation tallies and retraction alerts. Before committing, verify that your Zotero version is compatible with the local API and that the setup command detects your client; test the semantic extra on a sample collection because embedding models vary in quality and cost. The package is licensed MIT AND AGPL-3.0-or-later per pyproject.toml and actively updated; writes go either to a running Zotero 10+ after `zotero-mcp authorize-local` or through Zotero's web API, so check which applies to you first.
Frequently asked questions
Is there a Zotero MCP?
Yes. 54yyyu/zotero-mcp publishes an MCP server that installs as zotero-mcp-server from PyPI, and it also ships zotero-cli plus an agent skill as an alternative route for coding agents.
Can ChatGPT be integrated with Zotero?
ChatGPT is one of the named clients. Since it has no shell, the MCP server route applies rather than the agent skill, and the getting started guide covers the connection details.
Can Claude access Zotero?
Both Claude Desktop and Claude Code are supported. zotero-mcp setup auto-configures the desktop client, and the manual config block belongs in claude_desktop_config.json or ~/.claude.json depending on which one you run.
how to use zotero mcp
Install zotero-mcp-server, tick Allow other applications on this computer to communicate with Zotero under Settings then Advanced in Zotero 7 or newer, then run zotero-mcp setup. Writes additionally need zotero-mcp authorize-local on Zotero 10 or newer.
zotero mcp vscode
The README's client lists name Claude Desktop, Claude Code, ChatGPT, Codex, Cherry Studio, Chorus, Autohand, Cursor, Windsurf, Gemini CLI, Amp and OpenCode, and point other clients to the Getting started guide. The configuration is a command plus an env block, so identify which MCP client the editor actually runs before assuming support.
Official sources
Add this badge to your README
If you maintain this project, the badge below links readers to this analysis and shows its maintenance status from the daily GitHub snapshot. Paste the markdown into your README; add ?metric=license or ?metric=stars to the image URL for a different field.
[](https://hysenlabs.com/projects/54yyyu-zotero-mcp)Star history chart for your README
[](https://hysenlabs.com/projects/54yyyu-zotero-mcp)Was this useful?