How to Use the Zotero MCP in AutoGen

Q: How do I list all available tags using Zotero and AutoGen?

The listtags tool gathers every tag name in your library. This output can be passed to multiple agents, allowing them to debate the best tagging schema for a new project.

Q: Can I manage item deletion with Zotero and AutoGen?

Yes. You can use deleteitem or deleteitems within a multi-agent conversation. This allows one agent to confirm the deletion is irreversible, mimicking a final human sign-off.

Q: How do I list child items (notes/attachments) using Zotero and AutoGen?

Use listitemchildren against a specific item key. This allows your autonomous agents to gather all associated notes or attachments, providing full context for their debate.

Run multi-agent consensus on your research data using Zotero MCP Server with AutoGen.

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 AutoGen

Create your Vinkius account to connect Zotero to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Metadata Review

Need to validate a source? One agent can use `list_item_fields` to check what metadata is available. A second agent can then use that knowledge to run an `update_item`, ensuring all necessary fields are populated. This simulates human peer review, where multiple roles verify the data integrity.

Structured Source Identification with AutoGen

Start by calling `list_top_collections`. The agents then debate which collection is most relevant for the current project. Once a target folder is agreed upon, they use `list_collection_items` to pull the necessary list of sources. This process forces deliberation before any data fetching occurs.

Managing Library Integrity via MCP Server

The system can run a check using `get_item_type_fields` to verify if an item structure is correct. If the schema looks wrong, another agent can flag it and suggest remediation steps. It's built for consensus: confirming the validity of data before trusting any conclusions.

Setup guide

Set up Zotero MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Zotero tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Zotero_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Zotero data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Zotero_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Zotero data")
    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 AutoGen

The `list_tags` tool gathers every tag name in your library. This output can be passed to multiple agents, allowing them to debate the best tagging schema for a new project.

Yes. You can use `delete_item` or `delete_items` within a multi-agent conversation. This allows one agent to confirm the deletion is irreversible, mimicking a final human sign-off.

It manages core Zotero academic data—items, collections, and tags. The server provides structured metadata that multiple specialized agents can read and write to debate over.

Use `list_item_children` against a specific item key. This allows your autonomous agents to gather all associated notes or attachments, providing full context for their debate.

The server works with Zotero item objects. These contain structured fields like text notes, attachment references, and metadata arrays that are critical for multi-agent review.

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