Zotero MCP for AI. Manage and query your entire academic source library.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
Zotero manages your academic research library, allowing you to list collections, search specific items, and pull full bibliographic data directly through your AI agent.
You keep control of your entire source network without leaving your writing environment.
What your AI can do
Create items
Adds entirely new research sources to your Zotero library when the schema is properly provided.
Delete item
Removes a single source item from your collection permanently.
Delete items
Clears out up to 50 outdated or duplicate sources in one batch operation.
List every top-level collection or subcollection you own, giving you a map of your entire library structure.
Fetch the complete bibliographic details for any single source, including creator names and publication years.
Query thousands of items across your library using advanced filters based on tags or keywords.
Create new citations in the library, delete multiple old items at once, or update existing item details.
Ask an AI about this
Waiting for input…
Zotero MCP with 23 Tools
These tools let you perform every action in Zotero, from listing top-level collections to updating item metadata, all through natural conversation.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Zotero on VinkiusCreate Items
Adds entirely new research sources to your Zotero library when the schema is properly provided.
Delete Item
Removes a single source item from your collection permanently.
Delete Items
Clears out up to 50 outdated or duplicate sources in one batch operation.
Get Collection
Retrieves all items and details from a specific, named collection within the library.
Get Deleted
Shows you what sources were deleted since a certain point in your library's history.
Get Item
Fetches the full record and metadata for one specific source item using its unique key.
Get Item Type Fields
Lists all valid data fields that can be used when creating or modifying an item.
Get New Item Template
Generates a required JSON structure so you know exactly how to build a new citation...
Get Tag
Looks up all tags that match a specific name across the entire library.
List Collection Items
Retrieves a list of sources contained within one specific collection you identify.
List Collections
Provides an exhaustive list of every top-level research grouping in your library.
List Item Children
Shows all related notes, attachments, and sub-elements tied to a specific source item.
List Item Fields
Lists every available piece of data you can attach to any Zotero item.
List Item Tags
Returns all tags currently applied to a single, specific source item.
List Item Types
Provides an exhaustive list of all types of sources (book, article, etc.) in the...
List Items
Gathers a simple listing of every source item available in your entire Zotero...
List Publications
Lists all the sources you have marked as part of 'My Publications'.
List Subcollections
Shows all smaller, nested collections that belong to a larger main collection.
List Tags
Gathers every single tag used across your entire library for easy filtering.
List Top Collections
Retrieves a list of the main, highest-level groupings in your research library.
List Top Items
Gathers a simple list of all top-level sources that don't belong to any specific...
List Trash Items
Shows you every source item that has been moved to the trash bin.
Update Item
Makes partial changes, like adding notes or fixing a title, to an existing research...
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token
from cloud.vinkius.com. For OAuth-protected servers, expand
Advanced settings to add credentials.
Start a conversation
Open a new chat. The Zotero integration is available immediately — no restart needed.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Zotero, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Zotero. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 23 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Manually tracking sources is a nightmare of tabs and pop-ups.
Right now, managing your reading list means opening Zotero, navigating through collections, filtering by tag, and then manually pulling specific metadata for every single source you cite. You spend more time organizing the references than actually writing the paper.
With this MCP, those repetitive clicks disappear. Your agent can pull all necessary data—the full bibliographic details, the creator info, or even related notes—and hand it to your drafting tool in one go. The result is a clean flow from source material straight into your document.
The Zotero MCP gives you direct control over every piece of metadata.
You no longer have to rely on bulk exports or guesswork. You can specifically use list_item_fields to see exactly what data points are available, then use get_new_item_template to ensure your input is perfectly structured before creating a source with create_items.
What's different now is that the entire process—from discovery (list_top_collections) to modification (update_item)—is handled conversationally. It feels like having an expert research assistant sitting right next to you.
What your AI can actually do with this
You can connect your Zotero sources right into your workflow, letting your AI agent treat your reference library like any other data source. Instead of manually searching tabs or juggling PDF files, you ask your agent to pull specific details—like the full publication date and creator for a given item—or list all available notes attached to a key paper.
This capability means you can manage complex reading lists and organize entire research projects simply by talking to your AI client. Because credentials pass through Vinkius's zero-trust proxy, your sensitive API keys never sit on disk; they only move across the connection when needed. You get full control over everything in your library, from browsing top-level collections to finding specific items and managing tags.
019e3912-0ea9-7338-abab-8ba578db3875 
Here's how it actually works
The bottom line is you get immediate, conversational access to structured academic data without ever touching the Zotero desktop app.
First, subscribe to this MCP and provide your Zotero API Key and User ID.
Next, connect the service credentials from Claude, Cursor, or any compatible client through Vinkius.
Finally, prompt your agent with a request—like 'List all my sources related to machine learning'—and get instant data back.
Who is this actually for?
This connector is for anyone whose job requires intense source tracking: graduate students writing dissertations, researchers building literature reviews, or technical writers documenting complex systems. You're tired of exporting CSVs and manually checking links.
Using this MCP to quickly pull citation data for a new paper draft, ensuring all sources are correctly logged against specific project collections.
Asking the agent to list all reading materials tagged 'pre-read' and pulling their full bibliographic details before writing chapter three.
Managing a centralized, collaborative library of reference material for internal documentation that needs consistent citation tracking.
What Changes When You Connect
Stop juggling tabs. Instead of manually searching for sources, you can ask your agent to list all top-level collections or pull specific item details using get_item, keeping your work focused on writing, not finding files.
No more lost notes. You can use list_item_children to see every attachment and note linked to a source, making sure you never forget context for a key paper.
Build structured workflows that span multiple platforms. By combining this MCP with other tools—say, one that drafts text and another that manages citations—you build automations that keep all your sources centralized in Vinkius's secure environment.
Save time on cleanup. Instead of manually checking hundreds of files for duplicates, you can use delete_items to clear out old or redundant references in bulk.
Keep track of everything. You can list_tags and list_item_types to understand exactly how your library is structured, helping you organize future research efforts efficiently.
See it in action
The Literature Review Cleanup
A researcher realizes they have dozens of sources with the same topic but different citations. They ask their agent to list_tags for 'AI Ethics' and then use get_item on all resulting items to confirm which ones need updating, preventing citation errors.
The Thesis Outline Builder
A student is structuring a chapter. They prompt the agent to list top-level collections for 'Chapter 2: Methodology' and then use get_item on all items found there to gather specific metadata, building an instant source index.
The Source Audit
An academic needs to prove which sources were used in a paper. They ask the agent to list_item_children for key papers and confirm that all supporting documentation was correctly linked before submission.
The honest tradeoffs
Trying to find everything manually
You open Zotero, click on 'Collections,' then you have to check every single folder and subfolder just to find one specific tag or item.
Start by asking your agent to list_top_collections. If that doesn't work, ask it to list_tags first, which gives you a map of everything tagged, saving hours.
Updating sources one at a time
You find an item needs a title change and have to manually edit the record in Zotero's interface.
Use update_item by passing the key of the source you need changed. Your agent handles the partial update, saving you the manual click.
Assuming data is clean
You try to delete a bunch of old items without checking if they were linked elsewhere.
Before using delete_items, always check list_item_children or get_item on the target item first. This confirms nothing critical relies on that source.
When It Fits, When It Doesn't
Use this MCP if your primary need is managing a complex, structured library of academic sources and citations. You're dealing with fields like publication date, creator, tags, and nested collections. Don't use it if you just need to manage simple file folders; those are better handled by basic document storage connectors. If you only need to list generic items without deep metadata (like authors or dates), listing tools like list_items might suffice, but for true research work, this MCP gives the necessary depth via get_item and list_item_fields.
Questions you might have
Can I search for specific items in my library using keywords? +
Yes! Use the list_items tool with the q parameter. It performs a quick search across titles and creators to find exactly what you need.
How do I view the subcollections nested inside a main collection? +
Simply use the list_subcollections tool and provide the collection_key of the parent collection. The agent will return all nested folders.
Does this support shared group libraries or only my personal library? +
It supports both! Most tools, like list_collections or list_items, accept an optional group_id. If provided, the agent will query that specific group library instead of your personal one.
If I use get_item, how do I verify what specific fields or data points are available for that item type? +
You must first call list_item_fields to see every possible field name. This tells your agent exactly which metadata you can request when fetching an item.
What is the correct workflow if I want to create a new item using create_items? +
Start by calling get_new_item_template for the desired type. This provides the required JSON schema, ensuring your agent sends data in the proper format every time.
If I accidentally delete an item, can I use list_trash_items to recover it? +
Yes, using list_trash_items retrieves objects that were deleted. You can review these records and potentially restore them if needed.
When making changes to a single record, do I need to send the entire item data, or is there an easier way? Should I use update_item? +
You should use update_item. This tool handles partial updates (PATCH), meaning you only need to send the specific fields that changed, saving bandwidth and processing time.
How do I list all available tags across my entire Zotero library using list_tags? +
list_tags pulls a comprehensive list of every tag name used in your library. This lets your agent search or filter items based on any existing keyword.
We've already built the connector for Zotero. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 23 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.