How to Use the Zotero MCP in Vercel AI SDK

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

You trigger a general list command like listitems and then filter the results client-side. Since your agent streams the data, you can show the user which items match their query as soon as the first few records appear.

Q: Can I get metadata details with Zotero using Vercel AI SDK?

Yes. You run getitem by key to retrieve all structured data for a single reference. The streaming nature of the Vercel AI SDK means this detailed JSON payload arrives in chunks, which is perfect for populating specific form fields.

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

You just call listcollections. The agent fetches all top-level groups and streams them out. This is straightforward for building a navigation menu in your front-end application.

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

Absolutely. The deleteitems tool lets you remove up to 50 records at once, which is ideal for a batch cleanup feature in your user-facing product.

Stream real-time Zotero data into your UI using Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Zotero to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Displaying Library Contents in Real Time

Use `list_items` to fetch the core list of references from a user's library. When you call this tool, your AI client streams back every item name and key as it finds them, updating your UI instantly without waiting for a final 'loading complete' state. You can also run `list_collections` to show all available groups in the Zotero library, letting users see how their references are organized as they scroll through your React component.

Creating New Academic Records

The `get_new_item_template` tool lets you pull a JSON schema for any item type. This means when a user wants to add a new reference, your agent knows exactly what fields (like authors or dates) it needs to ask the user for. Once the data is collected, the `create_items` function handles adding the new record directly into Zotero's database via an authenticated call.

Managing Item Details and Fields

Need to know what metadata exists? Call `list_item_fields` to get a list of all available fields for any item type. This information lets your agent build accurate forms that match Zotero's internal structure. Furthermore, you can use `update_item` to make partial changes—like fixing an author name—without needing to overwrite the entire record.

Setup guide

Set up Zotero MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Zotero tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Zotero transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

You trigger a general list command like `list_items` and then filter the results client-side. Since your agent streams the data, you can show the user which items match their query as soon as the first few records appear.

Yes. You run `get_item` by key to retrieve all structured data for a single reference. The streaming nature of the Vercel AI SDK means this detailed JSON payload arrives in chunks, which is perfect for populating specific form fields.

You just call `list_collections`. The agent fetches all top-level groups and streams them out. This is straightforward for building a navigation menu in your front-end application.

Absolutely. The `delete_items` tool lets you remove up to 50 records at once, which is ideal for a batch cleanup feature in your user-facing product.

This server primarily touches structured metadata and text strings, specifically the item's core content (e.g., authors, titles, abstract text). You should never trust or display this raw data outside of your secure front-end context.

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