npx -y @oscardvs/zoteus

What it does

Zoteus connects an MCP client such as Claude Desktop, Claude Code, or Cursor to your Zotero library. It exposes 30 tools, namespaced zotero_*, that search the library by keyword or by meaning, return passages from your PDFs with page locators, format bibliographies with citeproc-js in any CSL style, add items by DOI or arXiv id, and create, edit, tag, and organize items with reversible writes. When the Zotero desktop app is running, reads and personal-library writes go to it directly and need no cloud API key; the Zotero Web API v3 is the fallback for sync, group libraries, and for when the app is closed. Zoteus is written in TypeScript, runs on your machine, and is MIT licensed.

Install

For normal use there is nothing to download from GitHub: your MCP client fetches Zoteus with npx the first time it runs. If you are new to MCP servers, start with docs/getting-started.md.

Updating a desktop-extension install: manually installed extensions (.mcpb, or the older .dxt) do not auto-update. Turn on Check for updates in the extension settings (or set ZOTEUS_UPDATE_CHECK=true) and Zoteus asks GitHub once a day, then tells you in-chat via zotero_whoami when a newer version exists; download the new zoteus.mcpb and reinstall it to upgrade. The check is off by default. npx installs always run the latest published version.

A cloud API key is optional. Add one for sync, group libraries, and writes when the desktop app is not running; reads and personal-library writes work without a key against a running Zotero.

claude mcp add --transport stdio zoteus -e ZOTERO_API_KEY=xxxxx -- npx -y @oscardvs/zoteus

Get a key at zotero.org/settings/keys. For key-free local reads and writes, enable Settings → Advanced → "Allow other applications on this computer to communicate with Zotero" in the desktop app.

Features

• Search your own library. Hybrid keyword and semantic search over titles, abstracts, creators, and tags, plus full-text keyword search inside your PDFs and notes, with the matching passage returned together with its page number. Your own notes and PDF annotations are indexed under the item they belong to, so "where did I object to this?" is a question search can answer. Set ZOTEUS_INDEX_FULLTEXT (or pass fulltext:true to zotero_index) and semantic search also covers the body of every PDF, so a claim that never made it into an abstract is still findable.
• Format citations. Zoteus reads the citation data in your Zotero library and formats it with citeproc-js in any CSL style from the CSL styles repository.
• Add a paper by identifier. Pass a DOI or arXiv id and Zoteus fetches the metadata and files the item. This works out of the box through built-in resolvers; a Zotero translation-server extends it to ISBN, PMID, and URLs (see docs/resolver.md).
• Write back. Create items, edit, tag, and organize. Writes are versioned with optimistic-locking retries, trash is reversible by default, and permanent deletion is opt-in and confirmation-gated.
• Write straight to the desktop app. Personal-library writes go to your running Zotero, with no cloud API key. On Zotero 10+ this uses the local API behind a key you grant once ("Always Allow"); on Zotero 9 and earlier, whose local API is read-only, it uses the connector protocol the browser extensions use. The cloud Web API is the fallback for group libraries and for when the app is not running.
• Annotate PDFs and attach files. zotero_annotate adds highlights, underlines, and notes, the same objects the Zotero PDF reader creates. Quote the passage and Zoteus locates it in the PDF and anchors the annotation to the lines it occupies, wrapping and hyphenation included, so no page coordinates are needed. zotero_attach_file stores a local file or a URL as an attachment under any item.
• Ground claims in the PDF. zotero_get_fulltext returns the relevant passage with character offsets, the nearest heading, and a page locator. When Zotero has not indexed the PDF or EPUB, it extracts the text on the fly, from the running desktop app or from Zotero's own storage folder, so a file added a minute ago is readable immediately. It also returns a PDF's table of contents (outline:true) and any page range on demand, so working through a 400-page book costs a few small calls rather than one that returns the whole book.
• Follow the literature. zotero_scholar looks up a paper's references, citing works, and related works through OpenAlex, with Crossref as a fallback, and can flag which of them are already in your library.
• Agent support. 30 tools with structured outputs, MCP Resources and Prompts, and a generated tool tree for the code-execution-with-MCP pattern.

How it works

1. Install with one npx command, or the one-click .mcpb.
2. Connect by running the desktop app for key-free local access, or by pasting your Zotero API key.
3. Ask. Your MCP client can now search, cite, add to, and organize your library.

Zoteus detects a running Zotero desktop app and talks to it directly: the key-free local API for reads (full PDFs, saved-search results, the semantic-search index build), and the app itself for personal-library writes (imports, annotations, attachments, trash). The cloud Web API v3 is the fallback, and it is still required for sync, group libraries, and writes when the app is not running. Details: docs/writing.md.

Semantic search setup. The first zotero_semantic_search builds the library index in the background. On very large libraries you can also run zotero_index (action:"build") yourself, then poll action:"status" until it is done. The build pages your library through the same local-first path as every other read, so it needs no cloud API key while the desktop app is running. That covers your personal library and, on Zotero 10+, any group library the app holds; a key is needed when the app is closed, and for a group the app does not hold.

Embedding through an API on a large library. A full-text build of a 10k-item library is tens of thousands of requests, and at the default pacing the rate rides at OpenAI's tokens-per-minute ceiling whatever your tier. A rate-limited request now backs off and retries rather than failing the build, and a build that still ends short keeps everything it indexed: run zotero_index action:"build" again and it resumes, embedding only the passages that have no vector yet (action:"refresh" is the one that starts over). To pace it up front, set ZOTEUS_EMBED_BATCH_SIZE=256 and ZOTEUS_EMBED_BATCH_DELAY_MS=8000. See docs/semantic-search.md.

Vector ranking is opt-in. Keyword (BM25) search works out of the box everywhere. On-device vectors need @huggingface/transformers, which the desktop-extension bundle cannot ship (the resolved dependency tree, onnxruntime's native binaries included, is about 700 MB): install it into a directory of its own (mkdir -p ~/.zoteus-deps && cd ~/.zoteus-deps && npm init -y && npm i @huggingface/transformers) and set ZOTEUS_TRANSFORMERS_PATH to ~/.zoteus-deps/node_modules. Not npm i -g: Claude Desktop runs the server on its own built-in Node, so a global install under a version manager sits next to a Node the extension never executes. When vectors are unavailable Zoteus says so in zotero_index status, zotero_whoami, and zotero_semantic_search rather than quietly returning nothing. See docs/semantic-search.md.

Configuration

Full table in docs/configuration.md. To run a shared or remote instance, see docs/remote-oauth.md (self-host the OAuth remote on loopback or behind your own proxy).

Documentation

zoteus.com/docs · Getting started · Configuration · Import & resolver · Architecture · Safe writes · Citations · Semantic search · Scholarly context · Code execution · Deployment

Privacy

Zoteus runs locally, collects nothing, and has no telemetry. Your library data flows only between your machine and the services you configure (Zotero, and optionally scholarly-graph or embedding providers), directly and under your own keys. Full policy: PRIVACY.md.

Contributing

Contributions are welcome; see CONTRIBUTING.md. Zoteus is MIT licensed.

Acknowledgements

Built on the Model Context Protocol, the Zotero Web API, citeproc-js, and the Citation Style Language. Not affiliated with or endorsed by the Corporation for Digital Scholarship / Zotero.