How to Use the Zenodo MCP in Vercel AI SDK

Q: How do I search Zenodo records using the Vercel AI SDK?

Call listrecords. This searches published content by ID. The results stream directly into your UI, letting you display the findings to the user immediately as they appear.

Q: Can I manage deposition lifecycle with Zenodo and Vercel AI SDK?

Yes. You can use tools like editdeposition or updatedeposition. These actions update a published resource, and the results stream back to your application instantly for confirmation.

Q: What if I need to find a specific deposition ID with Zenodo and Vercel AI SDK?

Use listdepositions first. This action retrieves a list of all known depositions, allowing you to grab the target ID needed for subsequent actions like viewing or editing.

Q: Does this MCP Server support versioning when working with Zenodo and Vercel AI SDK?

Absolutely. You can call newversiondeposition which handles creating a new, distinct version of an existing deposition without overwriting the old work.

Real-time data updates for 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 Zenodo MCP to Vercel AI SDK

Create your Vinkius account to connect Zenodo 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 Zenodo with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Read Zenodo Data Live with ai-sdk

Need to pull scientific records into a user interface? The `get_record` tool lets you fetch an existing Zenodo record by ID. Because this works with the Vercel AI SDK, the data streams directly to your React or Svelte UI—the user sees it appear live instead of waiting for a loading spinner. Use `list_records` when you need to search published content across Zenodo. This lets your agent quickly gather multiple potential results that you can then display in chunks as they arrive, making the whole experience feel fast and native.

Manage Deposition Status with MCP Server

Building a tool to manage user uploads? Start by using `list_depositions` to see all known deposition IDs. This initial list lets your agent figure out which resources need attention, whether they're drafts or published. When you call `get_deposition`, the results stream right into your UI. This is perfect for letting a user check the current status of their work—did they upload new files? Is it ready for review?—all in real-time.

Handle File Uploads with ai-sdk

If you need to add data, use `upload_deposition_file` to attach a text file to an existing Zenodo deposition. This action makes it simple for your agent to manage the actual content of the research record. For managing multiple files within one deposit, call `list_deposition_files`. The resulting list shows exactly what's attached right now, letting you confirm that all necessary components are accounted for before publishing.

Setup guide

Set up Zenodo 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 Zenodo 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 Zenodo 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 Zenodo. 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 Zenodo 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 Zenodo MCP in Vercel AI SDK

Call `list_records`. This searches published content by ID. The results stream directly into your UI, letting you display the findings to the user immediately as they appear.

Yes. You can use tools like `edit_deposition` or `update_deposition`. These actions update a published resource, and the results stream back to your application instantly for confirmation.

The server touches Deposition Metadata, uploaded Files, and Records. You can read or write this information using the MCP Server tools to keep track of what your agent is doing.

Use `list_depositions` first. This action retrieves a list of all known depositions, allowing you to grab the target ID needed for subsequent actions like viewing or editing.

Absolutely. You can call `new_version_deposition` which handles creating a new, distinct version of an existing deposition without overwriting the old work.

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