Zotero MCP Server for AutoGenGive AutoGen instant access to 23 tools to Create Items, Delete Item, Delete Items, and more

Name: Zotero
Price: 29 USD
Availability: InStock
Rating: 4.9 (1 reviews)
Author: Vinkius

GDPR Free for Subscribers

Microsoft AutoGen enables multi-agent conversations where agents negotiate, delegate, and execute tasks collaboratively. Add Zotero as an MCP tool provider through Vinkius and every agent in the group can access live data and take action.

Ask AI about this MCP Server for AutoGen

Open in ChatGPT Open in Claude Open in Perplexity

The Zotero MCP Server for AutoGen is a standout in the Productivity category — giving your AI agent 23 tools to work with, ready to go from day one.

Built for AI Agents by Vinkius

Vinkius delivers Streamable HTTP and SSE to any MCP client

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

+ other MCP clients

python

import asyncio
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.tools.mcp import McpWorkbench

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with McpWorkbench(
        server_params={"url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"},
        transport="streamable_http",
    ) as workbench:
        tools = await workbench.list_tools()
        agent = AssistantAgent(
            name="zotero_agent",
            tools=tools,
            system_message=(
                "You help users with Zotero. "
                "23 tools available."
            ),
        )
        print(f"Agent ready with {len(tools)} tools")

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Zotero MCP Server

Connect your Zotero library to any AI agent and take full control of your research workflow through natural conversation.

AutoGen enables multi-agent conversations where agents negotiate, delegate, and collaboratively use Zotero tools. Connect 23 tools through Vinkius and assign role-based access. a data analyst queries while a reviewer validates, with optional human-in-the-loop approval for sensitive operations.

What you can do

Collections & Organization — List top-level collections, subcollections, and specific collection details to navigate your library structure.
Item Management — Query all items, including notes and attachments, with support for advanced filtering by type, tag, or keyword.
Metadata Inspection — Fetch complete bibliographic data, creator information, and publication details for any specific item.
Tags & Publications — Access your personal publications and manage tags to categorize your research effectively.
Group Libraries — Seamlessly switch between your personal library and shared group libraries using specific IDs.

The Zotero MCP Server exposes 23 tools through the Vinkius. Connect it to AutoGen in under two minutes — credentials fully managed, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

All 23 Zotero tools available for AutoGen

When AutoGen connects to Zotero through Vinkius, your AI agent gets direct access to every tool listed below — spanning reference-management, citation-tools, academic-research, and more. Every call runs in a secure, isolated environment with full audit visibility. Beyond a simple connection, you get real-time monitoring of agent activity, enterprise governance, and optimized token usage.

create

Create items on Zotero

Use get_new_item_template first to get the correct schema. Create new items in the Zotero library

delete

Delete item on Zotero

Delete a single item

delete

Delete items on Zotero

Delete multiple items (up to 50)

get

Get collection on Zotero

Get a specific collection by key

get

Get deleted on Zotero

Get deleted objects since a specific library version

get

Get item on Zotero

Get a specific item by key

get

Get item type fields on Zotero

List valid fields for a specific item type

get

Get new item template on Zotero

Get a JSON template for creating a new item of a specific type

get

Get tag on Zotero

Get tags matching a specific name

list

List collection items on Zotero

List items in a specific collection

list

List collections on Zotero

List all collections in the Zotero library

list

List item children on Zotero

List child items (notes, attachments) for a specific item

list

List item fields on Zotero

List all available Zotero item fields

list

List item tags on Zotero

List tags for a specific item

list

List item types on Zotero

List all available Zotero item types

list

List items on Zotero

List items in the Zotero library

list

List publications on Zotero

List items in My Publications

list

List subcollections on Zotero

List subcollections of a specific collection

list

List tags on Zotero

List all tags in the library

list

List top collections on Zotero

List top-level collections in the Zotero library

list

List top items on Zotero

List top-level items in the Zotero library

list

List trash items on Zotero

List items in the trash

update

Update item on Zotero

Update an existing item (Partial Update / PATCH)

Connect Zotero to AutoGen via MCP

Follow these steps to wire Zotero into AutoGen. The entire setup takes under two minutes — your credentials stay safe behind Vinkius.

Install AutoGen

Run pip install "autogen-ext[mcp]"

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Integrate into workflow

Use the agent in your AutoGen multi-agent orchestration

Explore tools

The workbench discovers 23 tools from Zotero automatically

Why Use AutoGen with the Zotero MCP Server

AutoGen provides unique advantages when paired with Zotero through the Model Context Protocol.

Multi-agent conversations: multiple AutoGen agents discuss, delegate, and collaboratively use Zotero tools to solve complex tasks

Role-based architecture lets you assign Zotero tool access to specific agents. a data analyst queries while a reviewer validates

Human-in-the-loop support: agents can pause for human approval before executing sensitive Zotero tool calls

Code execution sandbox: AutoGen agents can write and run code that processes Zotero tool responses in an isolated environment

Zotero + AutoGen Use Cases

Practical scenarios where AutoGen combined with the Zotero MCP Server delivers measurable value.

Collaborative analysis: one agent queries Zotero while another validates results and a third generates the final report

Automated review pipelines: a researcher agent fetches data from Zotero, a critic agent evaluates quality, and a writer produces the output

Interactive planning: agents negotiate task allocation using Zotero data to make informed decisions about resource distribution

Code generation with live data: an AutoGen coder agent writes scripts that process Zotero responses in a sandboxed execution environment

Example Prompts for Zotero in AutoGen

Ready-to-use prompts you can give your AutoGen agent to start working with Zotero immediately.

"List all my top-level collections in Zotero."

"Search for items in my library with the tag 'artificial-intelligence'."

"Get the complete bibliographic details for item key ABCD1234."

Troubleshooting Zotero MCP Server with AutoGen

Common issues when connecting Zotero to AutoGen through Vinkius, and how to resolve them.

McpWorkbench not found

Install: pip install "autogen-ext[mcp]"

Zotero + AutoGen FAQ

Common questions about integrating Zotero MCP Server with AutoGen.

How does AutoGen connect to MCP servers?

Create an MCP tool adapter and assign it to one or more agents in the group chat. AutoGen agents can then call Zotero tools during their conversation turns.

Can different agents have different MCP tool access?

Yes. AutoGen's role-based architecture lets you assign specific MCP tools to specific agents, so a querying agent has different capabilities than a reviewing agent.