How to Use the Zotero MCP in Pydantic AI

Q: How do I search for specific references using Zotero and Pydantic AI?

Run the listitems tool; it fetches all records. Since every response is validated by Pydantic, your agent gets clean, structured data ready to use without guesswork.

Q: Is creating new data safe with Zotero and Pydantic AI?

It's extremely safe. When you call createitems, the tool validates against a template before committing anything. This means your research library stays clean, preventing bad or incomplete records.

Guaranteed data integrity for Zotero using Pydantic AI's type-safe MCP Server approach.

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 Pydantic AI

Create your Vinkius account to connect Zotero to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Maintain precise reference records

The `create_items` tool lets your agent add references, but it forces validation first. It uses `get_new_item_template` to pull the required schema, meaning if the data is missing a field, the process fails loudly—no silent errors. Need to change an item? Use `update_item`. Because of Pydantic AI's type-safety layer, you only pass fields that are expected and valid for the target item.

Audit and map library structure

Start by running `list_collections` to see the main containers. You can then check deeper groupings with `list_subcollections`. The MCP Server also lets you list all top-level items using `list_top_items`. For a complete view of item categories, use `list_item_types`, which tells your agent exactly what kind of reference it's dealing with.

Retrieve and manage metadata

To find out what fields are available for any given Zotero record, run `list_item_fields`. This structured data ensures the agent knows exactly how to read or write information. Tags are also managed precisely; use `get_tag` to find tags by name, or check all existing ones with `list_tags`.

Setup guide

Set up Zotero MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "zotero-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Zotero tools.",
)

result = await agent.run("List recent Zotero transactions")
print(result.output)

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 Pydantic AI

Run the `list_items` tool; it fetches all records. Since every response is validated by Pydantic, your agent gets clean, structured data ready to use without guesswork.

It's extremely safe. When you call `create_items`, the tool validates against a template before committing anything. This means your research library stays clean, preventing bad or incomplete records.

The server manages collections, subcollections, and top-level groups. You use `list_collections` to map out the entire hierarchy of your reference library.

The server handles Item Metadata, Tags, and Collection Keys. Because of Pydantic's validation layer, it enforces a rigid structure on all retrieved reference data.

Pydantic ensures that every response from the MCP Server—whether listing tags or updating an item—adheres to a defined Python model. This eliminates runtime errors caused by unexpected data formats.

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