How to Use the Zotero MCP in Google ADK

Q: How do I search and retrieve data with Zotero and Google ADK?

Your agent uses listitems to pull the current contents of your library. Because it connects via the MCP Server, it can handle large queries that feed into BigQuery for deeper analysis.

Q: What happens when I create new data with Zotero and Google ADK?

When you use createitems, the tool first validates against a template via getnewitemtemplate. This guarantees that the newly created references conform to expected standards before they are saved.

Q: Does Zotero handle sub-collections with Google ADK?

Absolutely. You can list all collections using listcollections, and then drill down into specific groupings using listsubcollections to map complex research hierarchies within the library.

Q: Can I list item details for a specific collection using Zotero and Google ADK?

Yes. You use listcollectionitems to see everything inside a defined collection, giving you a comprehensive overview of that section of your research library.

Scale your research operations across Google Cloud using the Google ADK for Zotero.

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 Google ADK

Create your Vinkius account to connect Zotero to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Examine entire reference sets

To get a full picture of your references, run `list_items` to list everything in Zotero. Need to focus on one area? Use `list_collections` or `list_top_collections`. The Google ADK lets you reason over these large data outputs. It’s also possible to see exactly what's been thrown out with the `list_trash_items` tool. This gives your agent a complete audit trail of all removed references.

Control item creation and modification

Building a new reference? Call `create_items`. The process requires `get_new_item_template` to validate the schema first. This prevents bad data from ever entering your library, which is crucial for enterprise use. If you find an old item that needs fixing, just pass the ID and fields into `update_item`. You can also delete items using `delete_items`, making sure your dataset stays clean.

Deep dive into Zotero structure

Want to know what fields are available for a specific item type? Run `list_item_fields`. This level of detail is key when building complex data pipelines. The server also exposes `list_item_types` so you can build specialized tools. Furthermore, if an item has associated notes or attachments, the `list_item_children` tool pulls all that nested information for comprehensive analysis.

Setup guide

Set up Zotero MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Zotero tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Zotero_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Zotero tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Your agent uses `list_items` to pull the current contents of your library. Because it connects via the MCP Server, it can handle large queries that feed into BigQuery for deeper analysis.

When you use `create_items`, the tool first validates against a template via `get_new_item_template`. This guarantees that the newly created references conform to expected standards before they are saved.

Absolutely. You can list all collections using `list_collections`, and then drill down into specific groupings using `list_subcollections` to map complex research hierarchies within the library.

It handles Zotero's core structure: Item Metadata, Tags, and Collection Keys. The server processes textual and structured reference information.

Yes. You use `list_collection_items` to see everything inside a defined collection, giving you a comprehensive overview of that section of your research library.

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