How to Use the Zotero MCP in Claude Code

Q: How do I list all collections using Zotero and Claude Code?

Run the command for listcollections. This executes in the terminal, giving you a clean, structured output of every top-level collection name. It's ideal for feeding into another script or cron job.

Q: Can Claude Code retrieve specific Zotero item data?

Yes. Use getitem to pull a single record by its key, or run listitems for a comprehensive list of records in the library. The output is always standardized JSON that your script can parse.

Q: What Zotero data types are visible to Claude Code?

You can get all available item types with listitemtypes. This tells you exactly what kind of records exist in the library. Then, use getitemtypefields on a specific type to see its required structure.

Q: How do I manage Zotero tags using Claude Code?

The terminal allows you to list all tags with listtags, or check for a specific tag by name using gettag. This makes automating the tagging process within your CI/CD pipeline reliable.

Run Zotero management tasks headless in Claude Code's terminal environment.

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 Claude Code

Create your Vinkius account to connect Zotero to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a citation pipeline.

You connect the script to Zotero and run it. It checks top-level collections with `list_top_collections`, then lists every item in them using `list_collection_items`. This is perfect for CI/CD pipelines where you need a full inventory report. Claude Code also lets you read individual item data using `get_item` or get the schema needed to create new items with `get_newitem_template`. You'll pipe clean, usable JSON output into your next stage.

Script bulk data cleanup.

Need to wipe out references? Run a script that uses `delete_items` to remove up to 50 records. It operates entirely in the terminal, perfect for scheduled jobs or maintenance scripts. If you want to audit what was deleted before running a destructive command, use `list_trash_items` or check history with `get_deleted`. The entire process runs headlessly.

Programmatically list metadata fields.

Writing an importer script? You must know the schema. Run a single command to get all available Zotero item fields using `list_item_fields`, or list every possible item type with `list_item_types`. The output is plain text ready for piping. This allows you to write scripts that validate data structure before committing changes via `update_item`.

Setup guide

Set up Zotero MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see zotero-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Zotero transactions." It will automatically discover and invoke the available Zotero tools.

Terminal

claude mcp add --transport http zotero-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Zotero MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "zotero-mcp": {
      "type": "url",
      "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 Claude Code

Run the command for `list_collections`. This executes in the terminal, giving you a clean, structured output of every top-level collection name. It's ideal for feeding into another script or cron job.

Yes. Use `get_item` to pull a single record by its key, or run `list_items` for a comprehensive list of records in the library. The output is always standardized JSON that your script can parse.

You can get all available item types with `list_item_types`. This tells you exactly what kind of records exist in the library. Then, use `get_item_type_fields` on a specific type to see its required structure.

The terminal allows you to list all tags with `list_tags`, or check for a specific tag by name using `get_tag`. This makes automating the tagging process within your CI/CD pipeline reliable.

The server handles reading item metadata, including collection keys and unique record identifiers. The specific data type exposed is structured reference material information.

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