How to Use the Zenodo MCP in AutoGen

Q: How can AutoGen manage dataset records with Zenodo?

Agents can use listrecords to gather available record IDs. They then pass these IDs to an agent that calls getrecord, ensuring all required data points are reviewed before a decision is made.

Q: How do I retrieve a specific record using Zenodo and AutoGen?

You initiate the process by having an agent call getrecord with the known ID. The resulting data is then passed to other agents for detailed analysis or comparison.

Facilitate consensus decisions with AutoGen and Zenodo data governance.

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 AutoGen

Create your Vinkius account to connect Zenodo to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debating Deposition Publication Status

You can set up agents to debate the best path for a dataset. One agent might call `list_depositions` to check current statuses, while another calls `get_deposition` to verify content integrity. The system forces deliberation on publishing; an 'Auditor' agent can challenge if `publish_deposition` is safe before proceeding.

Multi-Agent Data Review via MCP Server

Build a workflow where agents review data lifecycle events. One agent handles creating the initial draft using `create_deposition`, and another reviews the files uploaded via `upload_deposition_file`. They negotiate the final state. This is perfect for complex sign-off processes that require multiple perspectives.

Managing Data Versioning Consensus

Use AutoGen to simulate version control. Agents can debate whether a change requires `new_version_deposition` or if an update (`update_deposition`) is sufficient. They must agree on the correct tool call. This convergence process ensures that all parties sign off on the correct handling of data changes.

Setup guide

Set up Zenodo MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Zenodo tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Zenodo_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Zenodo data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Zenodo_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Zenodo data")
    print(result.messages[-1].content)

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 AutoGen

Agents can use `list_records` to gather available record IDs. They then pass these IDs to an agent that calls `get_record`, ensuring all required data points are reviewed before a decision is made.

Agents must coordinate through the rules: only unpublished depositions can be deleted, via `delete_deposition`. They'll have to verify status first.

It does. You build multi-step pipelines where agents pass results between tools—for instance, using `list_depositions` output as the input for an agent calling `edit_deposition`.

The server manages deposition metadata and file content. These are the key data types that agents debate, verify, and act upon during their workflow.

You initiate the process by having an agent call `get_record` with the known ID. The resulting data is then passed to other agents for detailed analysis or comparison.

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