Zenodo MCP for AI. Archive, search, and publish scientific datasets.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
Zenodo manages scientific datasets and research metadata. Connect your AI agent directly to the Zenodo platform to create, edit, search, and publish academic depositions and records through natural language conversation.
You can draft new work, update file contents, or list public data records without ever leaving your writing environment.
What your AI can do
Create deposition
Starts a brand new draft submission on Zenodo.
Delete deposition file
Takes a specific file out of a deposition package.
Delete deposition
Removes an unpublished deposition from your account.
Start and manage unpublished depositions, allowing you to add metadata and files before they are ready for review.
Search and list public records across Zenodo's massive database to find relevant research papers or datasets using simple queries.
Precisely control the titles, access rights, and descriptions of your work, even after it has been published.
List all specific files attached to a deposition so you know exactly what contents are part of the research package.
Create new versions of an existing deposition or publish your draft when it's ready for public access.
Ask an AI about this
Waiting for input…
Zenodo MCP: 14 Tools for Archiving Research Data
These tools give you fine-grained control over the entire research lifecycle. You can draft, upload files, manage metadata, and list records using specific commands.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Zenodo on VinkiusCreate Deposition
Starts a brand new draft submission on Zenodo.
Delete Deposition File
Takes a specific file out of a deposition package.
Delete Deposition
Removes an unpublished deposition from your account.
Discard Deposition
Reverts or cancels recent edits made to a deposition draft.
Edit Deposition
Makes changes directly to an existing, non-published deposition record.
Get Deposition
Retrieves all details for a specific deposition using its unique ID number.
Get Record
Gets the published metadata and status for a known Zenodo research record ID.
List Deposition Files
Provides a list of every file currently associated with a given deposition ID.
List Depositions
Retrieves a list of all the depositions you have created on Zenodo.
List Records
Searches and returns a list of published research records across the platform.
New Version Deposition
Creates an entirely new version history for an existing deposition record.
Publish Deposition
Makes your unpublished draft available to the public internet.
Update Deposition
Updates general metadata and information on a specific deposition draft.
Upload Deposition File
Adds a text file directly into an existing deposition package.
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token
from cloud.vinkius.com. For OAuth-protected servers, expand
Advanced settings to add credentials.
Start a conversation
Open a new chat. The Zenodo integration is available immediately — no restart needed.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Zenodo, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 14 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Every time you finish a research paper, you face the same tedious headache:
You write your findings and hit 'Save.' Then, you open Zenodo in another tab. You copy the metadata—the title, the creator list, the license details—and paste them into a form that has twenty required fields. You upload your files one by one, and then you have to manually check every field to make sure nothing is missing or wrong before hitting 'Submit' for archiving.
With this MCP, your agent handles all that messy data transfer behind the scenes. You just tell it what needs doing—like 'Draft a new deposition using these files.' The result isn't a series of clicks; it's a ready-to-use draft managed by your AI client.
Getting full control over your research lifecycle with the Zenodo MCP
You eliminate manual steps like opening the deposition dashboard, clicking 'Add File,' and then going back to change the license type. Instead, you simply ask for actions like `list_deposition_files` or run `update_deposition`, and the agent handles the complex sequence of API calls.
It’s about having an intelligent layer over a complex system. You manage your entire data lifecycle—from initial draft (`create_deposition`) to final versioning (`new_version_deposition`)—all without ever feeling lost in a web UI.
What your AI can actually do with this
This MCP lets you manage complex scientific archives using just talk-to-text commands. Need to start a research paper? Create an unpublished deposition draft in seconds. Found the perfect dataset for a project? List and find it across Zenodo's entire public record database. You can upload files, precisely update metadata like licenses or creators, and even create new versions of existing work without manual navigation through confusing web forms.
Since your credentials pass through Vinkius’s zero-trust proxy, your keys never sit on a disk, keeping sensitive research data secure throughout the process. Whether you're drafting an initial deposition or publishing a final dataset, this connector makes managing academic output feel like talking to a dedicated lab assistant.
019e3910-b951-7395-8ebd-cdaae1e36f28 
Here's how it actually works
The bottom line is you talk to your AI agent, and it handles all the complex API calls needed to manage your research data on Zenodo.
Subscribe to the MCP and provide your Zenodo Personal Access Token.
Tell your AI agent what you want to do—for example, 'Find all files related to my deposition ID 987654.'
The system executes the necessary commands, returns the data (e.g., a list of files), and completes the task in plain text.
Who is this actually for?
Academics, researchers, and data scientists who spend too much time clicking through web forms instead of writing papers. This is for anyone frustrated by the manual steps required to archive or publish scientific work.
Drafting a deposition requires updating metadata and uploading files, making sure every piece of documentation is correctly attributed.
Needs to quickly list or search for specific datasets across multiple records for a new analysis without using the web interface.
Manages deposition status, needs to verify which files are attached to a record, and ensure proper version tracking.
What Changes When You Connect
You can instantly generate a new draft using create_deposition, getting started on your research without leaving the chat window.
Instead of browsing through public searches, use list_records or get_record to quickly find specific published works and their metadata.
Need to make changes? You don't have to start over. Use update_deposition or edit_deposition to refine your work before publishing it with publish_deposition.
Keep a perfect audit trail by using new_version_deposition, ensuring every change is tracked and versioned.
The system handles file management, letting you use list_deposition_files to verify the contents of a package without opening any folders.
See it in action
I need to publish my research data but I'm worried about losing my changes.
A researcher drafts their work and adds several files. Before pressing the final 'publish' button, they want a safety net. They use new_version_deposition first, creating a backup version before calling publish_deposition, ensuring the original draft history remains intact.
I found an old dataset but I don't know if it was ever updated.
A data scientist finds a record ID and needs to check its status. They use get_record to retrieve the published metadata, giving them immediate confirmation of the record’s current state.
I need to add supplemental material to my existing draft.
A lab member realizes they forgot a key CSV file. They don't have to re-upload everything; they just use upload_deposition_file to add the missing data directly into the deposition package.
I need to verify what files are actually in my draft.
An archivist has a deposition ID and needs confirmation of contents. They use list_deposition_files, which provides an immediate list of all attached assets, helping them confirm the package integrity.
The honest tradeoffs
Using delete when discard is needed
The user thinks deleting a file means they can undo it later. They call delete_deposition_file on a draft, but realize minutes later that was the wrong action.
If you just want to throw out recent changes or revert your work without permanently deleting anything, always use discard_deposition. This keeps your history clean and recoverable.
Trying to edit a published record
The user finds an error in their live dataset and tries to call edit_deposition directly on the live link. The tool fails because published records are locked.
You cannot modify published records directly. Instead, use new_version_deposition first. This creates a controlled draft of the changes, which you can then review before calling publish_deposition.
Missing the full context
The user only knows a deposition ID but doesn't know if it was published or still in draft status.
Always call get_record first. This verifies the public metadata, while using get_deposition confirms its internal draft status.
When It Fits, When It Doesn't
Use this MCP if your core task involves managing structured scientific output: drafting, versioning, or archiving datasets and papers. You need to manage specific metadata fields like licenses or creators. Don't use it if you just want a general search of web articles; use a dedicated retrieval tool for that. If your goal is merely to view the public record without making any changes, get_record is sufficient. However, if your workflow involves multiple steps—for instance, searching records (list_records), getting details (get_record), and then finally publishing or updating them with new metadata—this MCP keeps all those actions in one place. The key boundary: this handles the lifecycle of scientific data, not general knowledge retrieval.
Questions you might have
How do I find old records using the Zenodo MCP? +
Use list_records or get_record. These tools search and retrieve published metadata from existing research artifacts, helping you track down specific public datasets.
Can I edit a file after publishing it with the Zenodo MCP? +
No. Once published, the record is locked for compliance reasons. You must use new_version_deposition to create an updated draft first; then you can publish that new version.
What do I use to start a brand new dataset submission? +
You call create_deposition. This drafts a new, unpublished record in your account. You'll then need to use tools like upload_deposition_file to add content.
Is there an easy way to see all my existing depositions? +
Yes, run list_depositions. It gives you a clear list of every deposition ID you have created and managed on the platform.
If I mess up my metadata while drafting, how do I revert those changes using the `discard_deposition` tool? +
Running discard_deposition immediately reverts your current draft to its last saved state. This is a quick way to wipe out unintended edits or incorrect inputs before you proceed with publishing or saving permanently.
What happens if I use the `delete_deposition` tool, and does it affect my files? +
The delete_deposition tool removes an unpublished draft entirely. It won't delete published records; this action is limited to drafts before they are finalized and submitted.
How do I create a formal, traceable update version using the `new_version_deposition` tool? +
The new_version_deposition tool makes a distinct copy of your current work. This is crucial because it keeps all historical versions accessible, even if you make major changes or publish subsequent updates.
What are the best practices for data security when running `upload_deposition_file`? +
While the MCP handles secure transmission, access control rests with Zenodo. Always review and set appropriate license terms and restricted permissions before uploading any sensitive files.
Can I delete a deposition that has already been published? +
No. The delete_deposition tool only works for unpublished depositions. Once a record is published on Zenodo, it is permanent to ensure scientific traceability.
How can I search for public datasets about a specific topic? +
You can use the list_records tool with a search query. For example, ask the agent to 'Search Zenodo records for climate change' and it will return matching public entries.
Is it possible to see which files are included in a deposition before downloading them? +
Yes! Use the list_deposition_files tool with the Deposition ID. The agent will provide a list of all filenames and metadata associated with that specific deposition.
We've already built the connector for Zenodo. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 14 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.