LLM for Zotero
A research agent system deeply rooted in your own Zotero library.
What is LLM for Zotero?
LLM for Zotero is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to research agent system deeply rooted in your own zotero library.
A research agent system deeply rooted in your own Zotero library.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A research agent system deeply rooted in your own Zotero lib
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx llm-for-zoteroConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use LLM for Zotero
LLM for Zotero is a Zotero plugin and research agent system that embeds LLM capabilities directly into your personal academic library. It supports paper summarization, multi-paper comparison, figure interpretation, and an agent mode that can search your library, retrieve PDF passages via RAG, update metadata, create notes, and sync outputs to Obsidian or Logseq. Researchers use it to have intelligent conversations with their literature collections, generate structured summaries, and query across dozens of papers without leaving Zotero.
Prerequisites
- Zotero 6 or Zotero 7 desktop application installed
- An API key from your LLM provider (OpenAI, Anthropic Claude, or a compatible provider with an OpenAI-compatible API)
- PDF attachments available in your Zotero library for full-text analysis
- Optional: Obsidian or Logseq for syncing generated notes to your knowledge base
Download the plugin XPI file
Go to the Releases page of the llm-for-zotero GitHub repository and download the latest .xpi plugin file.
# Visit: https://github.com/yilewang/llm-for-zotero/releases
# Download the latest .xpi fileInstall the plugin in Zotero
In Zotero, open the Add-ons manager and install the plugin from the downloaded file.
# In Zotero:
# Tools → Add-ons → click gear icon → Install Add-on From File
# Select the downloaded .xpi file and confirmConfigure your LLM provider
Open Zotero Preferences and navigate to the llm-for-zotero section. Enter your LLM provider's API base URL, secret key, and model name. Multiple providers can be configured simultaneously.
# In Zotero:
# Edit → Preferences → llm-for-zotero
# API Base URL: https://api.openai.com/v1 (or your provider's URL)
# Secret Key: your-api-key-here
# Model: gpt-4o (or claude-3-5-sonnet, etc.)Enable agent mode for library search
In the plugin preferences, enable agent mode to unlock tools that can search your library, retrieve specific PDF passages, apply tags, and manage notes programmatically.
Configure note export directory
If you want generated notes synced to Obsidian or Logseq, set the output directory in preferences to your vault's notes folder.
# In llm-for-zotero preferences:
# Output Directory: /path/to/your/obsidian-vault/Literature NotesLLM for Zotero Examples
Client configuration
MCP server configuration for llm-for-zotero if using it in MCP mode alongside Claude Desktop.
{
"mcpServers": {
"llm-for-zotero": {
"command": "npx",
"args": ["llm-for-zotero"],
"env": {
"ZOTERO_API_KEY": "your-zotero-api-key",
"LLM_API_KEY": "your-openai-or-anthropic-key",
"LLM_BASE_URL": "https://api.openai.com/v1",
"LLM_MODEL": "gpt-4o"
}
}
}
}Prompts to try
Example queries to run from the llm-for-zotero chat panel or agent mode.
- "Summarize this paper and save the summary as a Zotero note"
- "Compare the methodologies of the three papers I have selected"
- "Search my library for papers about attention mechanisms and list their key findings"
- "What does this figure on page 7 show? [attach screenshot]"
- "Summarize this paper and export the notes to my Obsidian vault with YAML frontmatter"Troubleshooting LLM for Zotero
Plugin fails to load or does not appear in Zotero after installation
Restart Zotero after installing the .xpi file. If the plugin still does not appear, check that you are running a compatible Zotero version (6 or 7) and that the .xpi file is not corrupted by re-downloading it from the Releases page.
LLM requests fail with authentication errors
Open Zotero Preferences → llm-for-zotero and verify the API Base URL format matches your provider (OpenAI: https://api.openai.com/v1, Anthropic-compatible: check provider docs). Ensure the Secret Key is copied without leading or trailing spaces.
Agent mode cannot find papers in my library
Agent mode uses RAG over your PDF attachments. Ensure the papers you want to search have PDF files attached in Zotero (not just web links). Papers with only metadata but no attached PDF cannot have their full text retrieved.
Frequently Asked Questions about LLM for Zotero
What is LLM for Zotero?
LLM for Zotero is a Model Context Protocol (MCP) server that research agent system deeply rooted in your own zotero library. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install LLM for Zotero?
Follow the installation instructions on the LLM for Zotero GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with LLM for Zotero?
LLM for Zotero works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is LLM for Zotero free to use?
Yes, LLM for Zotero is open source and available under the AGPL-3.0 license. You can use it freely in both personal and commercial projects.
LLM for Zotero Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to LLM for Zotero? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up LLM for Zotero in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use LLM for Zotero?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.