How to Use the Zenodo MCP in LangChain

Q: How do I search for past datasets using Zenodo and LangChain?

You call listrecords to search the public index. The output gives you a list of record IDs, which you can then pass into your agent's next step for deeper analysis.

Q: What happens if I publish a record using Zenodo and LangChain?

The data becomes fixed. The system warns you because once publishdeposition runs, calling deletedeposition is no longer possible. You'll have to manage changes through updates.

Q: Does the MCP Server support retrieving deposition metadata with Zenodo and LangChain?

Absolutely. Use getdeposition by ID. This pulls all the core metadata associated with a specific research effort, making it easy to log into your chain.

Build multi-step pipelines with LangChain and Zenodo's research data.

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 LangChain

Create your Vinkius account to connect Zenodo to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Research Cycles via MCP Server

Need to track a dataset from concept to publication? You can run full deposition workflows, starting by calling `create_deposition`. Later, you might use `upload_deposition_file` to add the final raw data set. This allows your agent to manage complex state changes. If things go wrong during an upload, you can call `discard_deposition` and try again without losing context.

Discover & Update Published Records

Looking for a specific dataset or record? Use `list_records` to search published Zenodo data. Once you find the ID, you can use `get_record` to pull all metadata and details. If the original research changes, call `update_deposition` directly on the existing record, ensuring your downstream systems always have the most current version.

Deposition Lifecycle Control

Handling deposition versions is straightforward. You can use `new_version_deposition` to create a new snapshot of your data without modifying the original source. This is key for auditing. When you're ready, remember that calling `publish_deposition` makes it permanent. After publishing, you must rely on tools like `edit_deposition` or `update_deposition`; deleting becomes impossible.

Setup guide

Set up Zenodo MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Zenodo tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "zenodo-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Zenodo transactions"
    })
    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 LangChain

You call `list_records` to search the public index. The output gives you a list of record IDs, which you can then pass into your agent's next step for deeper analysis.

Yes. If you need to change the contents of an existing file, use `update_deposition` or `upload_deposition_file`. You don't have to re-create the whole deposition.

The data becomes fixed. The system warns you because once `publish_deposition` runs, calling `delete_deposition` is no longer possible. You'll have to manage changes through updates.

Absolutely. Use `get_deposition` by ID. This pulls all the core metadata associated with a specific research effort, making it easy to log into your chain.

The server manages public and private deposition records and files. The primary data types are metadata (JSON/text) and text file content associated with scientific datasets.

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