How to Use the Zenodo MCP in CrewAI

Q: How do I start a research process with Zenodo and CrewAI?

Start by having an agent call listrecords. This allows the crew to gather a broad set of initial data points. The results can then be passed to another specialized agent for deep analysis.

Q: Can I track all files associated with a project using Zenodo and CrewAI?

Yes, use listdepositionfiles. This tool provides an inventory of every file attached to a deposition ID. It's crucial for the team monitor agent to ensure nothing was missed.

Q: If I need to change a published record with Zenodo and CrewAI?

You'll first use getrecord to pull the current details. Then, you can call updatedeposition or even newversiondeposition if a minor change isn't enough.

Autonomous research operations with CrewAI and Zenodo data tools.

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 CrewAI

Create your Vinkius account to connect Zenodo to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Dataset Research with MCP Server

Need specialized agents to find background context? The `list_records` tool lets a dedicated research agent search published Zenodo records. This output gives the analysis agent enough material to write its initial findings. Once the core record is identified, the agent uses `get_record` to pull all necessary details into shared memory for the next team member.

Build Full Lifecycle Pipelines with crewai

To document a new finding, Agent A can start by calling `create_deposition`. This initializes the workspace where subsequent agents will add data. After initial research, Agent B uses `upload_deposition_file` to attach supplementary reports. The MCP Server manages this process so the record is built layer by layer.

Manage and Publish Outputs with crewai

When all agents agree on the final data, one can call `update_deposition` to make minor tweaks before the grand finale. This ensures accuracy right up until the point of publication. The ultimate step is calling `publish_deposition`. This action marks the project as complete and available for public use across your autonomous operations.

Setup guide

Set up Zenodo MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Zenodo tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Zenodo Analyst",
    goal="Access and analyze Zenodo data via MCP.",
    backstory="Expert analyst with direct Zenodo access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Zenodo transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Zenodo Analyst",
        goal="Access and analyze Zenodo data via MCP.",
        backstory="Expert analyst with direct Zenodo access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Zenodo transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Start by having an agent call `list_records`. This allows the crew to gather a broad set of initial data points. The results can then be passed to another specialized agent for deep analysis.

Yes, use `list_deposition_files`. This tool provides an inventory of every file attached to a deposition ID. It's crucial for the team monitor agent to ensure nothing was missed.

The server handles Deposition Metadata, uploaded Files, and Records. Your multi-agent crew can read or write all three of these data types as part of its workflow.

You'll first use `get_record` to pull the current details. Then, you can call `update_deposition` or even `new_version_deposition` if a minor change isn't enough.

The server touches Deposition Metadata, uploaded Files, and Records. The autonomous operations must ensure that only necessary information is accessed or modified by the agents.

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