How to Use the Zotero MCP in LangChain

Q: How do I list all my top-level collections using Zotero and LangChain?

You just call the listtopcollections tool. It returns a clean list of every main folder in your Zotero library, giving you an overview before you dive into any specific project.

Q: Can I update item fields with Zotero and LangChain?

Absolutely. Use updateitem to make partial changes (a PATCH operation) to existing records. You don't have to touch the whole item; you can just fix one field, like adding a DOI or adjusting a date.

Q: How do I check if a specific item exists using Zotero and LangChain?

Call getitem by key. If the tool returns data, the item's there. If it fails or returns null, you know for sure that the reference is missing.

Manage your research pipeline with the Zotero MCP Server using LangChain.

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 LangChain

Create your Vinkius account to connect Zotero to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Complex Research Chains

The `list_collections` tool gives you a map of your entire library. You can then feed the name of one collection into `list_items` to get all contained items. This chain structure lets your agent figure out exactly where it needs to look next, making complex data retrieval simple.

Advanced Item Modification

Need to fix metadata? Use the `get_new_item_template` tool first. This provides a JSON schema you'll need for proper creation. After that, `update_item` lets your agent make targeted changes, like correcting an author name or adding keywords.

Monitoring Library Changes with MCP Server

The `get_deleted` tool tracks everything you've tossed since a specific library version. This is crucial for debugging research pipelines that might rely on deleted sources. Your agent can check the trash before proceeding, preventing it from trying to reference an item that no longer exists in your active Zotero collection.

Setup guide

Set up Zotero MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Zotero tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "zotero-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Zotero transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You just call the `list_top_collections` tool. It returns a clean list of every main folder in your Zotero library, giving you an overview before you dive into any specific project.

Absolutely. Use `update_item` to make partial changes (a PATCH operation) to existing records. You don't have to touch the whole item; you can just fix one field, like adding a DOI or adjusting a date.

It manages core Zotero data structures—items, collections, and tags. You'll be working with structured academic metadata, including authors, titles, publication dates, and associated notes.

Call `get_item` by key. If the tool returns data, the item's there. If it fails or returns null, you know for sure that the reference is missing.

This server works directly with Zotero item objects. This includes structured metadata like title strings, author arrays, and collection IDs.

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