How to Use the Zenodo MCP in OpenAI Agents SDK

Q: What is the safest way to modify a Zenodo deposition with the OpenAI Agents SDK?

Always use getdeposition first. Reviewing the current state ensures your agent knows exactly what it's working on before attempting an update via updatedeposition. This prevents unintended changes.

Q: Can I manage Zenodo deposition versions with the OpenAI Agents SDK?

Absolutely. The tool newversiondeposition lets your agent create a new version of any existing work. It’s critical for maintaining an auditable history of your scientific data.

Q: What if I need to delete unpublished Zenodo content using the OpenAI Agents SDK?

You must use deletedeposition on a deposition that hasn't been published. The system prevents deletion if you try it on live, public data.

Manage scientific datasets and records with the OpenAI Agents 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 OpenAI Agents SDK

Create your Vinkius account to connect Zenodo to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track and Publish Scientific Records via MCP Server

Use `create_deposition` to start a new Zenodo deposition, giving your agents immediate control over raw data uploads. You can then refine the record using `edit_deposition`, managing metadata before you hit publish. Need to update old work? The `new_version_deposition` tool lets your agent create an official version bump without deleting history. Remember: publishing a deposition is final; use `publish_deposition` only when ready.

Audit and Retrieve Data History

Your agent can list all existing work using `list_depositions`, giving you an overview of your current Zenodo footprint. If you need details on one specific project, call `get_deposition` with the ID to retrieve everything in one go. Keep track of what's inside by calling `list_deposition_files`. This lets your agent check exactly which files belong to a given deposition before moving forward.

Handle Data Updates and Disposal

If you mess up an edit, don't worry. The `discard_deposition` tool allows your agent to wipe out recent changes on a draft without affecting the published record. You can also manage file contents by calling `upload_deposition_file` or deleting specific files using `delete_deposition_file`. Remember that you can only delete an unpublished deposition using `delete_deposition`, and this action is blocked if it's already public.

Setup guide

Set up Zenodo MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Zenodo tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Zenodo tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Zenodo tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Zenodo Agent",
            instructions="You have access to Zenodo tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Your agent can search through published research records by calling `list_records`. This function searches across all of your work, letting you pinpoint specific datasets that were previously deposited.

Always use `get_deposition` first. Reviewing the current state ensures your agent knows exactly what it's working on before attempting an update via `update_deposition`. This prevents unintended changes.

Absolutely. The tool `new_version_deposition` lets your agent create a new version of any existing work. It’s critical for maintaining an auditable history of your scientific data.

You must use `delete_deposition` on a deposition that hasn't been published. The system prevents deletion if you try it on live, public data.

This server handles metadata and file contents related to scientific datasets (Zenodo depositions). It manages structured text data used for deposition records, which are unique identifiers.

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