Zotero MCP
Related Servers
Alternatives to Zotero MCP
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceAn MCP server that gives AI agents read access to a Zotero library, enabling search, item metadata, collections, tags, notes, and full-text search of attached PDFs.MIT
- AlicenseNot gradedqualityAmaintenanceMCP server that exposes 45 tools for Zotero reference management, enabling AI agents to read/write items, search, extract PDF text, and manage workspaces via the Zotero CLI.211AGPL 3.0
- AlicenseNot gradedqualityDmaintenanceMCP server that connects AI assistants to your Zotero library, enabling full-text PDF extraction and metadata search.MIT
- AlicenseAqualityCmaintenanceA lightweight MCP server that connects AI agents to a local Zotero library for paper management and metadata retrieval. It enables users to search titles and abstracts, browse collections, and automatically ingest papers via arXiv ID or DOI with PDF attachments.815MIT
- AlicenseAqualityAmaintenanceMCP server that lets AI assistants search, create, organize, and cite from a Zotero library.394MIT
- AlicenseAqualityAmaintenanceAn MCP server that lets AI assistants add papers and books to your Zotero library by DOI, arXiv ID, or ISBN, and manage your collections, tags, and items.502MIT
TDQS
Scored across 41 tools
Each tool targets a distinct resource and action, and the many search/read tools are explicitly differentiated by purpose (substring vs. tag vs. structured vs. semantic search; metadata vs. fulltext vs. outline vs. page-range reading). Cross-references in descriptions steer the agent to the right tool, so overlap is minimal.
All names use snake_case with a uniform `zotero_` prefix and mostly follow verb_noun (get_item_metadata, create_collection, delete_item). A few deviations (write_capabilities, advanced_search, semantic_search, manage_note) are minor but prevent a perfect 5.
41 tools is far above the typical 3–15 range and exceeds the 25+ threshold for 'too many'; despite the broad Zotero domain, the surface is granular enough that agent selection becomes burdensome. Several tools could be grouped behind modes (e.g., PDF operations, search variants) or conditionally loaded.
The surface covers full CRUD for items, collections, annotations, and notes, plus attachment handling, multiple search backends, semantic indexing, bibliography export, library switching, and authentication. No major lifecycle gap is apparent for core Zotero workflows.