How to Use the Zotero MCP in LlamaIndex

Q: How do I get a list of my top-level items using Zotero and LlamaIndex?

You use listtopitems to gather the initial set of sources. These item details are then fed into the index, making them searchable for future queries.

Q: Can I search tags across my library with Zotero and LlamaIndex?

Yes. The listtags tool provides all available tag names. Indexing these allows you to query not just the sources, but also which specific topics they are marked with.

Q: How do I find specific item types using Zotero and LlamaIndex?

Use listitemtypes to see every category of source you have. This helps you structure the data ingestion process before indexing any particular set of items.

Build a knowledge base from your research using the Zotero MCP Server with LlamaIndex.

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 LlamaIndex

Create your Vinkius account to connect Zotero to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Grounding Answers in Research Data

When you run `list_items`, LlamaIndex indexes all the resulting metadata. You can then query past sessions and get answers grounded in actual Zotero data, eliminating guesswork. Instead of guessing what a source means, your RAG app uses the indexed item details to provide verifiable context.

Analyzing Collection Structures via MCP Server

Need to understand how your library is organized? Call `list_collections` and then `list_subcollections`. These lists become part of a unified index, allowing you to semantically search across the entire hierarchy. This capability lets LlamaIndex treat your whole Zotero setup like one massive, searchable knowledge graph.

Retrieving Specific Metadata

To get details on a single source, use `get_item` with its unique key. The output is indexed and available for deep semantic search. This means you can ask, 'What sources mention quantum computing?' and the index pulls all relevant item data.

Setup guide

Set up Zotero MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Zotero MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Zotero tools.",
)
response = await agent.run("List recent Zotero data")

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 LlamaIndex

You use `list_top_items` to gather the initial set of sources. These item details are then fed into the index, making them searchable for future queries.

Yes. The `list_tags` tool provides all available tag names. Indexing these allows you to query not just the sources, but also which specific topics they are marked with.

It manages core Zotero data: items, collections, and tags. The server provides structured academic metadata that gets turned into searchable chunks for your vector store.

Use `list_item_types` to see every category of source you have. This helps you structure the data ingestion process before indexing any particular set of items.

The server handles Zotero item objects, which contain structured fields like dates, authors, and titles. These are the core academic records that get indexed.

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