# Zenodo MCP > 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. ## Overview - **Category:** knowledge-management - **Price:** Free - **Tags:** open-access, research-data, metadata-management, archiving, data-repository ## Description 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 Create an unpublished deposition draft in seconds.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. ## Tools ### 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 ### delete_deposition Removes an unpublished deposition from your account. ### 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 ### publish_deposition Makes your unpublished draft available to the public internet.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. ## Prompt Examples **Prompt:** ``` Search for public Zenodo records related to 'machine learning in healthcare'. ``` **Response:** ``` I've found several records. The most relevant include 'Dataset for ML in Clinical Diagnosis' (ID: 789012) and 'Survey of Healthcare AI' (ID: 345678). Would you like more details on any of these? ``` **Prompt:** ``` Create a new Zenodo deposition for a dataset titled 'Global Temperature Trends 2023'. ``` **Response:** ``` I've created a new unpublished deposition for you. The Deposition ID is 1234567. You can now start adding creators or uploading files to this draft. ``` **Prompt:** ``` List all files currently attached to my deposition with ID 987654. ``` **Response:** ``` Checking deposition 987654... I found 3 files: 'raw_data.csv', 'analysis_script.py', and 'metadata.json'. Would you like to update any of these or add more? ``` ## Capabilities ### Drafting New Research Submissions Start and manage unpublished depositions, allowing you to add metadata and files before they are ready for review. ### Finding Public Data Records Search and list public records across Zenodo's massive database to find relevant research papers or datasets using simple queries. ### Updating Dataset Metadata Precisely control the titles, access rights, and descriptions of your work, even after it has been published. ### Tracking File Changes List all specific files attached to a deposition so you know exactly what contents are part of the research package. ### Versioning and Publication Create new versions of an existing deposition or publish your draft when it's ready for public access. ## Use Cases ### 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. ## Benefits - 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. ## How It 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. 1. Subscribe to the MCP and provide your Zenodo Personal Access Token. 2. Tell your AI agent what you want to do—for example, 'Find all files related to my deposition ID 987654.' 3. The system executes the necessary commands, returns the data (e.g., a list of files), and completes the task in plain text. ## Frequently Asked Questions **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.