How to Use the Zotero MCP in Cline

Q: What Zotero data types can Cline handle?

Cline reads all available item types via listitemtypes, letting you know exactly what kinds of records exist. Then, it checks the specific fields for a type using getitemtypefields so your code knows where to write the data.

Execute Zotero library management tasks with Cline's autonomous coding agent.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Zotero MCP to Cline

Create your Vinkius account to connect Zotero to Cline and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Zotero with Cline

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a citation data dashboard.

Tell Cline to build the component, and it does it. It can pull all top-level collections using `list_top_collections`, then iterate through those to list every item in each collection via `list_collection_items`. You'll get structured output ready for a data visualization layer. This execution is end-to-end. Cline doesn't just report; it handles the full sequence, checking individual reference details with `get_item` and managing large lists using `list_items`.

Archive or purge old references.

Need to clean up a massive dataset? Cline can handle bulk deletion. You tell it the range, and it deletes multiple items (up to 50) using `delete_items`. It's perfect for running cleanup scripts in a CI/CD pipeline. If you need to know what was deleted before running a script, use `get_deleted` after specifying a library version. Cline makes sure the execution is verifiable.

Script out metadata fields.

Don't manually check every field; let Cline write the code for it. It lists all available item fields using `list_item_fields`, giving you a programmatic dictionary of what data points exist in Zotero. This is great for writing migration scripts. It also lets you get templates for new items with `get_newitem_template`. You can then write code that enforces the correct schema before creating records via `create_items`.

Setup guide

Set up Zotero MCP in Cline

Prerequisites

VS Code with Cline extension installed
Active Vinkius subscription with a valid endpoint token

1

Open Cline MCP settings

Click the Cline icon in the VS Code sidebar to open the Cline panel. Then click the MCP Servers icon (server stack) at the top-right corner of the panel.
2

Add a remote server

Click "Remote Servers" at the top, then click "Add Remote MCP". In the Name field, type zotero-mcp. In the URL field, paste your Vinkius endpoint: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp. Get your token from cloud.vinkius.com.
3

Enable the server

After saving, the server appears in the Cline MCP panel. Toggle the switch to enable it. The status indicator turns green when the connection is live.
4

Start using tools

Return to the Cline chat and ask: "Check my latest Zotero refund status." Cline will discover the available tools and request your approval before invoking each one — giving you full control over every action.

Cline MCP Settings

{
  "mcpServers": {
    "zotero-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Zotero now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Zotero MCP in Cline

Just tell Cline to run a script against it. It executes the command to gather every collection name with `list_collections`. This gives you a full inventory of your research library's structure.

Absolutely. You tell Cline to retrieve an item by its unique key using `get_item`, or if you need to check a whole collection, it runs `list_collection_items`. The output is clean JSON that's ready for your code.

Cline reads all available item types via `list_item_types`, letting you know exactly what kinds of records exist. Then, it checks the specific fields for a type using `get_item_type_fields` so your code knows where to write the data.

Yeah, you can programmatically manage tags. It fetches all tags in the library with `list_tags`, or it finds specific tags matching a name using `get_tag`. This makes scripting classification easy.

It treats deleted records like any other data source. You can script the retrieval of trashed items using `list_trash_items`, or check for objects that were deleted since a specific library version with `get_deleted`.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript