Zotero MCP
Zotero MCP acts as a powerful bridge between a personal research library and AI assistants like Claude or ChatGPT. It allows researchers to interact with their Zotero collections through natural conversation, making it easy to find specific papers, get summaries of articles, or analyze citations without manually digging through folders. …
About this Protocol
How to Use
1. Installation
Requirements:
* Python 3.10+
* Zotero 7+ (for local API with full-text access)
Via uv (Recommended):
uv tool install "git+https://github.com/54yyyu/zotero-mcp.git"
zotero-mcp setup
Via pip:
pip install git+https://github.com/54yyyu/zotero-mcp.git
zotero-mcp setup
Via Smithery (for Claude Desktop):
npx -y @smithery/cli install @54yyyu/zotero-mcp --client claude
2. Configuration
Automatic Configuration
Run the following command to auto-configure supported clients like Claude Desktop:
zotero-mcp setup
Claude Desktop (Manual)
Add the following to your claude_desktop_config.json:
{
"mcpServers": {
"zotero": {
"command": "zotero-mcp",
"env": {
"ZOTERO_LOCAL": "true"
}
}
}
}
Cherry Studio (Manual)
Go to Settings -> MCP Servers -> Edit MCP Configuration and add:
{
"mcpServers": {
"zotero": {
"name": "zotero",
"type": "stdio",
"isActive": true,
"command": "zotero-mcp",
"args": [],
"env": {
"ZOTERO_LOCAL": "true"
}
}
}
}
Remote Web API Setup
If using the Web API instead of a local Zotero instance:
zotero-mcp setup --no-local --api-key YOUR_API_KEY --library-id YOUR_LIBRARY_ID
3. Available Tools
Semantic Search Tools
zotero_semantic_search: AI-powered similarity search with embedding models.zotero_update_search_database: Manually update the semantic search database.zotero_get_search_database_status: Check database status and configuration.
Search Tools
zotero_search_items: Search library by keywords.zotero_advanced_search: Perform complex searches with multiple criteria.zotero_get_collections: List collections.zotero_get_collection_items: Get items in a collection.zotero_get_tags: List all tags.zotero_get_recent: Get recently added items.zotero_search_by_tag: Search library using custom tag filters.
Content Tools
zotero_get_item_metadata: Get detailed metadata (supports BibTeX export viaformat="bibtex").zotero_get_item_fulltext: Get full text content.zotero_get_item_children: Get attachments and notes.
Annotation & Notes Tools
zotero_get_annotations: Get annotations (including direct PDF extraction).zotero_get_notes: Retrieve notes from your Zotero library.zotero_search_notes: Search in notes and annotations.zotero_create_note: Create a new note for an item (beta).
4. Example Prompts
- "Search my library for papers on machine learning."
- "Find recent articles I've added about climate change."
- "Summarize the key findings from my paper on quantum computing."
- "Extract all PDF annotations from my paper on neural networks."
- "Search my notes and annotations for mentions of 'reinforcement learning'."
- "Export the BibTeX citation for papers on machine learning."
- "Find papers conceptually similar to deep learning in computer vision." (Semantic Search)
- "Research that relates to the intersection of AI and healthcare." (Semantic Search)
- "Papers that discuss topics similar to this abstract: [paste text]" (Semantic Search)
Use Cases
Use Case 1: Conceptual Literature Discovery and Gap Analysis
Problem: Researchers often struggle to find relevant papers when they don't know the exact keywords used in a different sub-field. Standard keyword search fails to connect "Deep Learning" with "Connectionist Models" or "Neural Networks" if the specific terms aren't present in the title.
Solution: This MCP uses Semantic Search to find research based on conceptual meaning rather than just keywords. It allows users to query their library using natural language descriptions or even by pasting an abstract from a new paper to see what similar work they already own.
Example: A user asks Claude: "Find papers in my library conceptually similar to this abstract: [pasted abstract about reinforcement learning in robotics].". The AI identifies relevant papers even if they use different terminology like "autonomous agent control" or "markov decision processes."
Use Case 2: Automated Synthesis of PDF Annotations for "Related Work"
Problem: Writing the "Related Work" section of a thesis or paper requires opening dozens of PDFs, manually copying highlights, and trying to find common themes among scattered notes.
Solution: The MCP can extract PDF annotations and notes across an entire collection. This allows an AI assistant to aggregate your personal insights, highlights, and comments into a structured summary or a first draft of a literature review.
Example: A user prompts: "Extract all my highlights and annotations from the papers in my 'Quantum Computing' collection. Group them by their approach to error correction and summarize my personal notes on each."
Use Case 3: Streamlined Citation Management for Developers
Problem: Developers writing technical documentation or research papers in Markdown/LaTeX editors (like Cursor or VS Code) often have to leave their environment, open Zotero, find a paper, and manually export the BibTeX citation.
Solution: This MCP allows users to retrieve BibTeX metadata directly within their AI-powered IDE or chat interface. You can find the paper and get the correctly formatted citation without breaking your flow.
Example: While writing a README in Cursor, the developer asks: "Find the paper I added yesterday about 'Fast Fourier Transforms' and give me its BibTeX citation." The AI returns the BibTeX block ready to be pasted into a .bib file.
Use Case 4: Deep Content Q&A across a Research Library
Problem: When a researcher remembers seeing a specific dataset or experimental result but can't remember which paper it was in, they have to manually search through dozens of full-text PDFs.
Solution: By leveraging full-text extraction and advanced search, the AI can act as an expert librarian that has "read" your entire collection. It can pinpoint specific mentions of methodologies, datasets, or niche variables across your library.
Example: A researcher asks: "Which of my papers on 'Neuroscience' mention using the 'Allen Brain Atlas' dataset? Summarize how they used it." The AI searches the full text of all relevant items and provides a comparative summary.
Use Case 5: Organizing and Cleaning Large Research Libraries
Problem: Over time, research libraries become cluttered with hundreds of papers that lack proper tags, making it difficult to maintain an organized system for long-term projects.
Solution: Using the metadata and tagging tools, an AI assistant can analyze your recent additions and suggest appropriate tags or move items into the correct collections based on their content.
Example: A user tells the AI: "Look at the last 20 papers I added. Based on their abstracts, suggest three tags for each and tell me if any belong in my 'LLM Safety' collection instead of the main library."