How to Use the Zotero MCP in CrewAI

Q: How do I search references with Zotero using CrewAI?

You assign a 'Research Agent' to run listitems. This agent searches the full library and hands back the matching records. The shared memory then allows other agents, like an 'Analysis Agent', to process those results immediately.

Q: Can I retrieve metadata details with Zotero using CrewAI?

Yes. The agent can invoke getitem on a specific key. This provides the full structured data, which is then passed to subsequent agents for analysis or formatting. It's highly reliable.

Q: If I need to list collections with Zotero using CrewAI, what tools do I use?

The 'Coordinator Agent' runs listcollections to map the organizational structure. If you need more detail, it can follow up by calling listsubcollections on any given group.

Q: Does the Zotero MCP Server support bulk operations with CrewAI?

The system supports this via deleteitems, which handles removing up to 50 records. This makes it perfect for an autonomous cleanup crew that runs scheduled maintenance.

Run autonomous Zotero library management with CrewAI's specialized agents.

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 CrewAI

Create your Vinkius account to connect Zotero to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Collection Building

You assign a 'Librarian Agent' to use `get_new_item_template` first. This agent determines the exact data structure needed for a new reference. A second 'Data Entry Agent' then runs `create_items`, completing the record creation autonomously. The whole operation is managed by shared memory, ensuring that if one step fails, the next specialized agent knows exactly where the process left off.

Deep Library Inventory and Auditing

The 'Auditor Agent' can run `list_items` to get a full inventory. It then runs secondary checks using tools like `list_item_types` or `list_item_fields`. This role-based approach means specialized agents handle specific data points, making the process robust. The system even allows for monitoring actions on trash items via `list_trash_items`, treating it like a normal part of the research cycle.

Controlled Reference Modification

Need to fix a reference? The 'Editor Agent' uses `update_item` with precise instructions, only changing the required fields. This targeted action prevents accidental data loss across the entire record. Because it’s an autonomous operation, you can define a sequence: list items -> identify outdated records using `list_tags` -> update those records in one pass.

Setup guide

Set up Zotero MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Zotero tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Zotero Analyst",
    goal="Access and analyze Zotero data via MCP.",
    backstory="Expert analyst with direct Zotero access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Zotero transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Zotero Analyst",
        goal="Access and analyze Zotero data via MCP.",
        backstory="Expert analyst with direct Zotero access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Zotero transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You assign a 'Research Agent' to run `list_items`. This agent searches the full library and hands back the matching records. The shared memory then allows other agents, like an 'Analysis Agent', to process those results immediately.

Yes. The agent can invoke `get_item` on a specific key. This provides the full structured data, which is then passed to subsequent agents for analysis or formatting. It's highly reliable.

The 'Coordinator Agent' runs `list_collections` to map the organizational structure. If you need more detail, it can follow up by calling `list_subcollections` on any given group.

The system supports this via `delete_items`, which handles removing up to 50 records. This makes it perfect for an autonomous cleanup crew that runs scheduled maintenance.

This server deals with structured metadata and text strings, specifically the item's core content (e.g., authors, titles, abstract text). Because the agents operate autonomously, you must ensure all operations respect user permissions on this sensitive academic data.

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