Zotero
Zotero MCP integrates AI assistants with Zotero reference management through the Model Context Protocol by providing a plugin with an embedded MCP server that enables searching, extracting content and annotations from PDFs, browsing collections, performing semantic searches, and managing library metadata. The server allows AI applications like Claude to interact directly with local Zotero libraries for literature reviews, citation management, content analysis, and knowledge base organization through tools for multi-dimensional search, full-text extraction, annotation analysis, and write operations.
- GitHub stars
- 784
- tools
- 21
- last updated
- Dec 15, 2025
Tools
21 toolsPublic tool metadata for what this MCP can expose to an agent.
search_libraryAdvanced library search with multi-dimensional filtering, boolean operators, relevance scoring, and intelligent mode control.
Advanced library search with multi-dimensional filtering, boolean operators, relevance scoring, and intelligent mode control.
No parameter schema in public metadata yet.
search_annotationsSearch annotations by query, colors, or tags with intelligent ranking.
Search annotations by query, colors, or tags with intelligent ranking.
No parameter schema in public metadata yet.
search_fulltextFull-text search across all document content with context snippets.
Full-text search across all document content with context snippets.
No parameter schema in public metadata yet.
search_collectionsSearch collections by name. Params: q, limit.
Search collections by name. Params: q, limit.
No parameter schema in public metadata yet.
get_item_detailsGet complete metadata for a single item. Params: itemKey (required), mode.
Get complete metadata for a single item. Params: itemKey (required), mode.
No parameter schema in public metadata yet.
get_item_abstractGet item abstract/summary. Params: itemKey (required), format (json/text).
Get item abstract/summary. Params: itemKey (required), format (json/text).
No parameter schema in public metadata yet.
get_contentUnified content extraction: PDF full-text, notes, abstracts, webpage snapshots from items or specific attachments.
Unified content extraction: PDF full-text, notes, abstracts, webpage snapshots from items or specific attachments.
No parameter schema in public metadata yet.
get_collectionsGet all collections. Params: mode, limit, offset.
Get all collections. Params: mode, limit, offset.
No parameter schema in public metadata yet.
get_collection_detailsGet details of a specific collection. Params: collectionKey (required).
Get details of a specific collection. Params: collectionKey (required).
No parameter schema in public metadata yet.
get_collection_itemsGet items in a collection. Params: collectionKey (required), limit, offset.
Get items in a collection. Params: collectionKey (required), limit, offset.
No parameter schema in public metadata yet.
get_subcollectionsGet subcollections. Params: collectionKey (required), limit, offset, recursive.
Get subcollections. Params: collectionKey (required), limit, offset, recursive.
No parameter schema in public metadata yet.
semantic_searchAI-powered semantic search using embedding vectors. Finds conceptually related content even without exact keyword matches.
AI-powered semantic search using embedding vectors. Finds conceptually related content even without exact keyword matches.
No parameter schema in public metadata yet.
find_similarFind items semantically similar to a given item.
Find items semantically similar to a given item.
No parameter schema in public metadata yet.
semantic_statusGet semantic search service status and index statistics. No parameters required.
Get semantic search service status and index statistics. No parameters required.
No parameter schema in public metadata yet.
fulltext_databaseAccess cached full-text content database (read-only).
Access cached full-text content database (read-only).
No parameter schema in public metadata yet.
write_noteCreate or modify Zotero notes. Supports Markdown auto-conversion to HTML.
Create or modify Zotero notes. Supports Markdown auto-conversion to HTML.
No parameter schema in public metadata yet.
write_tagAdd, remove, or replace tags on items.
Add, remove, or replace tags on items.
No parameter schema in public metadata yet.
write_metadataUpdate metadata fields on items (title, abstract, date, DOI, creators, etc.).
Update metadata fields on items (title, abstract, date, DOI, creators, etc.).
No parameter schema in public metadata yet.
write_itemCreate new items, reparent existing attachments, or import local files as attachments.
Create new items, reparent existing attachments, or import local files as attachments.
No parameter schema in public metadata yet.
add_by_identifierImport items by identifier (DOI, arXiv, ISBN, PMID, ADS bibcode) using Zotero's native resolvers.
Import items by identifier (DOI, arXiv, ISBN, PMID, ADS bibcode) using Zotero's native resolvers.
No parameter schema in public metadata yet.
trash_itemMove one or more items to Zotero Trash. Items stay recoverable until the user empties Trash; permanent deletion is not supported.
Move one or more items to Zotero Trash. Items stay recoverable until the user empties Trash; permanent deletion is not supported.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Zotero MCP - Model Context Protocol Integration for Zotero
Zotero MCP is an open-source project designed to seamlessly integrate powerful AI capabilities with the leading reference management tool, Zotero, through the Model Context Protocol (MCP). This project consists of two core components: a Zotero plugin and an MCP server, which work together to provide AI assistants (like Claude) with the ability to interact with your local Zotero library.
This README is also available in: :cn: 简体中文 | :gb: English.
Details
- Repository
- github.com/cookjohn/zotero-mcp
- Categories
- Documents & Knowledge, Search & Web Crawling
Related Documents & Knowledge MCP servers
View all
PDF Readersylphlab/pdf-reader-mcpProvides a production-ready MCP server to extract text, images, and metadata from PDFs via parallel processing across multiple sources.711stars
Obsidian Claude Codeiansinnott/obsidian-claude-code-mcpProvides a dual-transport MCP server for Claude Code and Claude Desktop to read and write your Obsidian vault via MCP.287stars
MCP LogSeq Serverergut/mcp-logseqMCP server to interact with LogSeq via its Local HTTP API - enabling AI assistants like Claude to seamlessly read, write, and manage your LogSeq graph.267stars
Zotero MCPkujenga/zotero-mcpSearch your Zotero library, retrieve item metadata, and read full text from AI assistants.162stars
Markdown Vault MCPpvliesdonk/markdown-vault-mcpGeneric markdown vault MCP with hybrid search38stars