# 54yyyu/zotero-mcp

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.

Repository: https://github.com/54yyyu/zotero-mcp
Canonical: https://ross.abutalabs.com/products/zotero-mcp
Homepage: https://stevenyuyy.com/zotero-mcp/
Language: Python
License: MIT
License Family: permissive
Topics: claude, mcp, zotero, semantic-search
Last push: 2026-08-25T02:00:54+00:00

## Health v2 (maintenance only)
Score: 87/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 99, longevity 37
- inputs: {"age_days": 529, "days_push": 9, "days_rel": 8, "gap_med": 7.0, "n_releases_24m": 21}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4796, forks 381 (observed 2026-08-28T04:08:59.924926+00:00)

## What it is
A Model Context Protocol (MCP) server that connects a Zotero research library to AI assistants like Claude, ChatGPT, Cursor, and Cherry Studio. It exposes tools for searching the library, retrieving full text and metadata, extracting PDF annotations, semantic vector search, and write operations like adding papers by DOI or URL.

## Use cases
- chat with my zotero library in claude
- find papers about a topic in my research library
- get ai summaries of papers in zotero
- extract pdf annotations and highlights from zotero
- export citations as bibtex through an ai assistant
- add papers to zotero by doi with auto-fetched metadata
- semantic search over my research papers
- analyze citations and related work with an llm

## When to choose
- you use Zotero and want an AI assistant to search, summarize, or discuss your library
- you need semantic/vector search across papers with local or cloud embedding models
- you want to extract PDF annotations, notes, and full text into LLM workflows
- you want write access from an AI client: adding papers by DOI/URL, managing collections and tags

## When to avoid
- you don't use Zotero or an MCP-compatible AI client
- you need a standalone reference manager rather than an AI integration layer
- you require remote access with full attachment support (Web API mode has limited attachment support)

## Facets
- artifact type: service
- maturity: active
- function: mcp, search-engine, rag, pdf, nlp
- domain: artificial-intelligence, large-language-models, developer-tools, education
- platform: python, cross-platform, cli, self-hosted
- tags: zotero, model-context-protocol, claude, chatgpt, semantic-search, research-library, bibtex, academic-writing, pdf-annotations, embeddings, ai-agents, search

## Member repositories
- 54yyyu/zotero-mcp (main) score 87

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:59.924926+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:18:39.240235+00:00, confidence not recorded.
  - readme: https://github.com/54yyyu/zotero-mcp (fetched 2026-08-28T04:08:59.924926+00:00, sha fd553bf14605)
  - homepage: https://stevenyuyy.com/zotero-mcp/ (fetched 2026-08-29T09:01:45.013140+00:00, sha a0209ebdcd24)
  - site_page: https://stevenyuyy.com/zotero-mcp/installation.html (fetched 2026-08-29T09:01:45.022261+00:00, sha cc6c78bfc80e)
  - site_page: https://stevenyuyy.com/zotero-mcp/api.html (fetched 2026-08-29T09:01:45.024075+00:00, sha 3c315fb5af5f)
- Data as of 2026-08-30T08:39:29.467469+00:00.