zotero-mcp MCP — Cas d'usage, Installer & Démo en direct

Pourquoi l'utiliser

Fonctionnalités clés

Installs as a Zotero plugin (.xpi), no separate server process
20 tools: search, semantic search, full-text, annotations, notes, tags
Reads cached PDF full text from Zotero's database
100% local — library data never leaves your machine

Démo en direct

Aperçu en pratique

zotero.replay ▶ prêt

0/0

Installer

Choisissez votre client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "zotero": {
      "command": "npx",
      "args": [
        "-y",
        "zotero-mcp"
      ],
      "_inferred": true
    }
  }
}

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "zotero": {
      "command": "npx",
      "args": [
        "-y",
        "zotero-mcp"
      ],
      "_inferred": true
    }
  }
}

Cursor utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la globale.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "zotero": {
      "command": "npx",
      "args": [
        "-y",
        "zotero-mcp"
      ],
      "_inferred": true
    }
  }
}

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "zotero": {
      "command": "npx",
      "args": [
        "-y",
        "zotero-mcp"
      ],
      "_inferred": true
    }
  }
}

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "zotero",
      "command": "npx",
      "args": [
        "-y",
        "zotero-mcp"
      ]
    }
  ]
}

Continue utilise un tableau d'objets serveur plutôt qu'une map.

~/.config/zed/settings.json

{
  "context_servers": {
    "zotero": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "zotero-mcp"
        ]
      }
    }
  }
}

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

claude mcp add zotero -- npx -y zotero-mcp

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

Cas d'usage

Usages concrets : zotero-mcp

How to draft a literature review from your Zotero library

👤 Researchers, PhD students, analysts ⏱ ~45 min intermediate

Quand l'utiliser : You've collected 50+ papers on a topic in Zotero and need to synthesize them into a coherent review.

Prérequis

Zotero desktop with zotero-mcp plugin installed — Download .xpi from releases, Tools → Add-ons → Install from file
PDFs attached and indexed — Right-click collection → Rebuild Full-Text Index if search is empty

Déroulement

Scope the review

Semantically search my Zotero collection 'Agentic AI' for papers on tool selection strategies. Return top 15.✓ Copié

→ Ranked list with titles, authors, year, abstract snippet
Extract key claims per paper

For each of those 15, read the full text and extract (a) the main claim, (b) method, (c) dataset or setting.✓ Copié

→ Structured table you can sort
Synthesize with citations

Write a 3-page review clustering these by approach. Cite every claim with Zotero item keys in (Author, Year) style.✓ Copié

→ Draft with bracketed citations mapping back to your library

Résultat : A first-draft review grounded in papers you actually own, every claim traceable to a Zotero item.

Pièges

Full-text search returns nothing — Zotero only indexes text-layer PDFs. Run OCR on image PDFs first
Citations hallucinated — Ask for the Zotero item key (e.g. ABCD1234) alongside every citation — you can paste it into a verifier

Combiner avec : arxiv

Summarize your highlights across a Zotero collection

👤 Avid readers, knowledge workers ⏱ ~20 min beginner

Quand l'utiliser : You've highlighted things across 30 books/papers and want a thematic summary.

Déroulement

Pull annotations by color/tag

Search my yellow highlights in collection 'Product Strategy'. Return the highlighted text plus the parent item.✓ Copié

→ List of highlights grouped by source
Cluster into themes

Cluster the highlights into 5-7 themes. For each theme, give a 2-sentence synthesis with the source items.✓ Copié

→ Themed notes with citations

Résultat : Scattered highlights turned into a personal knowledge-base note.

Combiner avec : anytype

Auto-tag and annotate newly added Zotero papers

👤 Library maintainers ⏱ ~15 min intermediate

Quand l'utiliser : You drop papers into a 'Unsorted' collection and want them triaged weekly.

Déroulement

List items added this week in 'Unsorted'

List Zotero items added in the last 7 days to my 'Unsorted' collection.✓ Copié

→ Inbox of new items
Generate tags and a 1-line summary per item

For each, propose 3-5 tags and a 1-line summary based on abstract. Apply them via the write tools.✓ Copié

→ Items now tagged; summary saved as a note attachment

Résultat : A self-maintaining Zotero library with consistent tagging.

Pièges

Write tools modify your library irreversibly — no undo — Run against a test collection first, or back up zotero.sqlite before enabling writes

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

zotero + arxiv

Arxiv-first exploration then auto-save to Zotero for reading

Find 10 recent arxiv papers on retrieval-augmented agents, then add the ones I don't already have to my 'Agents' Zotero collection.✓ Copié

zotero + anytype

Literature notes live in Anytype; source PDFs stay in Zotero

For the top 10 papers in my 'Agents' collection, create an Anytype page per paper with the summary and a backlink to the Zotero item key.✓ Copié

Outils

Ce que ce MCP expose

Outil	Entrées	Quand appeler	Coût
search_library	query: str, filters?: { collection, tag, itemType }	Text/metadata search across your library	0 — local DB
search_fulltext	query: str	Search inside PDF bodies (only indexed text layers)	0
semantic_search	query: str, top_k?: int	Concept-level match instead of keyword	0 — local embeddings
search_annotations	color?, tag?, query?	Pull your highlights/notes	0
get_item_details	item_key: str	Expand a reference from a search hit	0
get_content	item_key or attachment_key	Feed the full paper to Claude	0

Coût et limites

Coût d'exécution

Quota d'API: None — fully local
Tokens par appel: Full PDF fetches can hit 30k+ tokens; chunk before feeding
Monétaire: Free (Zotero is free; the plugin is MIT)
Astuce: Prefer search_fulltext returning snippets over get_content returning the whole PDF

Sécurité

Permissions, secrets, portée

Stockage des identifiants : None — plugin runs inside Zotero; local HTTP on 127.0.0.1:23120

Sortie de données : None in read mode; writes modify zotero.sqlite locally

Dépannage

Erreurs courantes et correctifs

MCP client can't connect on port 23120

Open Zotero → Preferences → Zotero MCP Plugin → verify 'Enable server' is checked and port isn't blocked

Vérifier : curl http://127.0.0.1:23120/health

Full-text search returns empty

PDF has no text layer. Right-click item → Reindex Item, or run OCR via Zotero's built-in OCR

Write operations forbidden

Enable write mode in plugin preferences — off by default for safety

Alternatives

zotero-mcp vs autres

Alternative	Quand l'utiliser	Compromis
Official Zotero Web API	You need cloud sync access from a remote server	Requires API key; rate-limited; no semantic search
Readwise MCP	Your highlights live in Readwise not Zotero	Cloud-based, subscription required

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills