How to Use the Zotero MCP in Mastra AI

Q: How do I search references with Zotero using Mastra AI?

You define a sequence of calls that use listitems and then filter the results within your workflow logic. The agent handles this iterative process reliably, guaranteeing you get all matching records.

Q: Can I retrieve metadata details with Zotero using Mastra AI?

Yes. Run getitem to fetch a reference's data payload. Since your workflow engine manages state, the resulting structured JSON is immediately available for use in subsequent steps or decision points.

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

You start by calling listcollections. This reliable tool fetches the entire collection structure. Your workflow can then branch out to call listsubcollections for deep analysis of any specific group.

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

It does. The deleteitems tool handles removing up to 50 records in a single, guaranteed transaction. This makes batch cleanup safe and predictable within your workflow.

Build resilient Zotero library management workflows with Mastra AI.

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 Mastra AI

Create your Vinkius account to connect Zotero to Mastra 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automating Reference Collection

You can initiate a complex workflow to build new references using `get_new_item_template`. This starts by fetching the required data structure, and then the agent uses `create_items` to commit the record. If the API call fails due to bad data, Mastra AI handles the retry automatically. The system can even be set up for conditional branching: if an item creation fails, it notifies you via a secondary endpoint instead of just failing the whole workflow.

Comprehensive Library Audits

The `list_items` tool retrieves every reference in the library. You can then build a multi-step flow that iterates through all records and checks their status using other tools like `list_item_tags`. This audit process is reliable, even if some API calls time out; Mastra AI retries until success. Need to find everything deleted? Use `get_deleted` to recover objects since a specific library version.

Complex Item Modification

Updating an existing entry isn't simple. The `update_item` tool lets you perform partial updates (PATCH), which is crucial for keeping track of changes without losing other data points. This reliable, single-command process ensures accuracy. If a required field for the update fails validation, Mastra AI catches the error and allows your workflow to continue or escalate to human approval.

Setup guide

Set up Zotero MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Zotero tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "zotero-mcp-client",
  servers: {
    "zotero-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Zotero Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Zotero tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Zotero transactions"
);
console.log(result.text);

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 Mastra AI

You define a sequence of calls that use `list_items` and then filter the results within your workflow logic. The agent handles this iterative process reliably, guaranteeing you get all matching records.

Yes. Run `get_item` to fetch a reference's data payload. Since your workflow engine manages state, the resulting structured JSON is immediately available for use in subsequent steps or decision points.

You start by calling `list_collections`. This reliable tool fetches the entire collection structure. Your workflow can then branch out to call `list_subcollections` for deep analysis of any specific group.

It does. The `delete_items` tool handles removing up to 50 records in a single, guaranteed transaction. This makes batch cleanup safe and predictable within your workflow.

This server manages structured metadata and text strings, specifically the item's core content (e.g., authors, titles, abstract text). Because of the sensitivity of academic research, you must ensure all transfers are handled within secure, private endpoints.

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