mcp-zotero
PyPI
v0.3.0
Published by nealcaren — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
MCP server for Zotero — library tools + optional semantic search
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 6.3 = 94. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −6.3 | Unsafe deserialization MTC-SRC-007 | permissions |
2. Client adoption risk — 94 − 4 = 90. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −3 | capability blast radius (moderate) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
In the server's implementation (`src/mcp_zotero/rag/vector_store.py:55`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: self._chunks = pickle.load(f) self._rebuild_indices() else: self._embeddings
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/mcp_zotero/rag/vector_store.py
Each tool and what it can reach — statically extracted from the published source.
download_attachmentsingests untrusted inputadd_itemno sensitive capabilityadd_item_to_collectionno sensitive capabilityattach_fileno sensitive capabilityattach_linked_fileno sensitive capabilitycollection_itemsno sensitive capabilitycollection_items_topno sensitive capabilitycollection_tagsno sensitive capabilitycreate_collectionsno sensitive capabilitycreate_saved_searchno sensitive capabilitycreator_fieldsno sensitive capabilitydelete_collectionno sensitive capabilitydelete_itemno sensitive capabilitydelete_saved_searchno sensitive capabilitydelete_tagsno sensitive capabilitydeleted_itemsno sensitive capabilityfind_similar_chunksno sensitive capabilityget_chunk_contextno sensitive capabilityget_collectionno sensitive capabilityget_itemno sensitive capabilityhealth_checkno sensitive capabilityindex_itemsno sensitive capabilityindex_libraryno sensitive capabilityindex_statusno sensitive capabilityitem_attachment_link_modesno sensitive capabilityitem_creator_typesno sensitive capabilityitem_fieldsno sensitive capabilityitem_tagsno sensitive capabilityitem_type_fieldsno sensitive capabilityitem_typesno sensitive capabilitylist_collectionsno sensitive capabilitylist_collections_subno sensitive capabilitylist_collections_topno sensitive capabilitylist_groupsno sensitive capabilitylist_indexed_itemsno sensitive capabilitylist_searchesno sensitive capabilitylist_tagsno sensitive capabilitypingno sensitive capabilityremove_from_indexno sensitive capabilityremove_item_from_collectionno sensitive capabilitysearch_itemsno sensitive capabilitysemantic_searchno sensitive capabilitytop_itemsno sensitive capabilitytrash_itemsno sensitive capabilityupdate_collectionno sensitive capabilityupdate_itemno sensitive capabilityScan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.3.0 latest |
A 90/100 | 1 | 1.13.0 | 2026-08-25 |
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan mcp-zotero --online --registry pypi
Independent packages implementing the same tool, scanned with the same engine. Compare all 7 side by side →
MCP server for Zotero.
Model Context Protocol server for Zotero integration that lets Claude interact with your Zotero library.
Unofficial MCP server for Zotero integration with citation management
Model Context Protocol server for Zotero
Zotero MCP Server for managing reference library
A Model Context Protocol server for Zotero
Hotel booking MCP server — 300K+ properties, real confirmation numbers, loyalty programs. Builders monetize every booking via Stripe Connect. The first MCP server that completes real hotel reservations inside AI conversations.
Manage AdGuard Home through AI assistants
Read-only Azure DevOps for MCP clients using only your existing browser session — no PAT, no Azure CLI. Browse work items, pull requests, comments, attachments and Artifacts feeds across every project, repo and feed you can access.
MCP server for Adobe Experience Manager Assets integration development
Servidor MCP para el tiempo oficial de España (API pública OpenData de AEMET). Predicción, observación y avisos como herramientas MCP tipadas.
A standalone MCP stdio bridge for Affinity by Canva's local MCP SSE server.