Zotero MCP
Related Servers
Alternatives to Zotero MCP
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityDmaintenanceConnects your Zotero research library with AI assistants (Claude, ChatGPT, etc.) via the Model Context Protocol, enabling paper review, summaries, annotations, and semantic search both locally and through the web API.MIT
- AlicenseNot gradedqualityBmaintenanceEnables natural language interaction with Zotero libraries, allowing users to search, retrieve, and update papers and metadata via AI assistants like Claude and Gemini.1GPL 2.0
- AlicenseNot gradedqualityCmaintenanceConnects Zotero to Claude Desktop, allowing Claude to read, search, and organize a user's Zotero library through local and web APIs.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to search, access, and interact with your Zotero research library, including semantic search, metadata retrieval, PDF annotations, and library management.MIT
- FlicenseBqualityDmaintenanceEnables AI assistants to search, cite, and manage research references directly from a Zotero library.99-
- AlicenseAqualityAmaintenanceEnables AI agents to search, read, annotate, and manage a local Zotero library via the Model Context Protocol, with full local storage and no cloud dependency.38MIT
TDQS
Scored across 41 tools
Every tool targets a distinct resource/action pair, and the few overlapping families (search variants, note vs annotation readers) are explicitly cross-referenced with 'use X instead' guidance. No two tools are interchangeable, so an agent can reliably select the right one.
All 41 tools share a uniform `zotero_` prefix and a predictable verb_noun pattern (get_, create_, update_, delete_, search_, list_, switch_, set_, manage_). Even the search family follows the pattern consistently (search_items, search_by_tag, search_collections), with only minor generic verbs like manage_note that still fit the style.
At 41 tools the set is too large for smooth agent operation; many subfamilies (search variants, PDF reading, status/infrastructure) could be consolidated into fewer parameterized tools. The breadth is real, but the count exceeds even the 'heavy' range and will burden context and tool-picking.
The surface covers items, collections, notes, annotations, attachments, libraries, tags, bibliography export, batch updates, auth, and search — essentially full CRUD/lifecycle for the domain. Minor gaps exist (e.g., no standalone note creation without a parent item, no direct 'list all library items' endpoint), but they are workaroundable.