Figshare MCP for AI. Manage your entire research publication lifecycle.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
Figshare manages your entire research publishing lifecycle directly through an AI agent. You can list public articles, create private drafts, manage complex data uploads, and organize collections without leaving your chat window.
This MCP lets you control metadata and track scholarly outputs for researchers and data teams.
What your AI can do
Complete file upload
Finalizes a data transfer that was previously initiated for an article.
Create collection
Builds a new public grouping of related scholarly outputs.
Create private article
Generates a draft article in your account that is not visible to the public yet.
The agent finds and lists every article currently marked as public on your Figshare profile.
You can draft a new, unpublished article in your account that you'll fill out later.
Initiate large file uploads for articles or list all existing datasets associated with a specific publication.
Change the title, description, and custom fields of an existing article to improve search visibility.
Create new themed groups or formal projects to keep related datasets and articles together.
Ask an AI about this
Waiting for input…
Figshare Tools (20)
Use these 20 tools to interact with every aspect of your research data, from listing public collections to updating individual article fields.
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 Figshare on VinkiusComplete File Upload
Finalizes a data transfer that was previously initiated for an article.
Create Collection
Builds a new public grouping of related scholarly outputs.
Create Private Article
Generates a draft article in your account that is not visible to the public yet.
Create Project
Sets up a new formal container for related research outputs and datasets.
Delete Article
Removes an existing article from your Figshare account.
Get Article Downloads
Pulls the total count of times an article has been downloaded.
Get Article
Retrieves all the specific details for one published article ID.
Get Article Views
Provides the cumulative number of views for a specific article.
Get Custom Fields
Fetches extra, institution-specific metadata fields associated with your account.
Get File Details
Retrieves specific information about a file uploaded to Figshare.
Get Hrfeed Upload
Gets details regarding an HR feed upload process.
Initiate File Upload
Starts the multi-part file transfer necessary for a new article draft.
List Article Files
Shows all files that are currently attached to an existing article.
List Public Articles
Retrieves a list of articles you have published publicly.
List Public Collections
Lists all public collections that you've created to organize content.
List Public Projects
Shows a list of publicly visible research projects.
Search Articles
Performs advanced text and metadata searches across your published articles.
Search Collections
Searches through collections based on keywords or criteria you provide.
Search Projects
Executes an advanced search across all your defined research projects.
Update Article
Modifies the title, description, or other metadata of an existing article.
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 Figshare 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 Figshare, 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 Figshare. 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 20 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
The pain of context switching is real.
Today, managing research data means opening Figshare in one tab, Excel for metadata tracking in another, and a separate dashboard just to check download stats. You copy the title from one place, paste it into another, manually update the description fields, and then remember to go back and run a file status check on a completely different platform. It's clicks, tabs, and painful manual syncing.
With this MCP, you keep all that logic contained in your chat window. You tell the agent what needs doing—whether it’s updating metadata or listing every associated file for audit—and you get confirmation right here. Your AI acts like a dedicated research data manager who lives inside your IDE.
The Figshare MCP gives you total control over article and project publication.
You no longer need to manually navigate the web interface to check if an uploaded file successfully completed its transfer, or to locate which specific collection a particular dataset belongs to. The agent handles those lookups for you using tools like `list_article_files` and `search_collections`.
What's different now is that your entire publishing workflow becomes conversational. You dictate the outcome; the MCP executes the complex sequence of API calls behind the scenes.
What your AI can actually do with this
Got a mountain of research files and need to keep your academic output organized? This connector links directly to your Figshare account, turning tedious repository navigation into natural conversation. You can manage everything from drafting private articles to publishing public datasets—all through your AI client. Instead of logging into a dashboard just to check a file upload status or tweak an article's title, you ask the agent.
It handles it. Need to track usage? Get total views and download counts for any piece of published work. You can also build structured knowledge by creating new projects or collections to group related research outputs. When working with complex data sets, Vinkius makes this MCP available in your preferred AI client, so you don't have to switch tools just to manage metadata.
019e3896-2a57-73ad-be2d-97e7fbe850fa 
Here's how it actually works
The bottom line is you manage your entire research repository by talking to your AI client instead of clicking through web interfaces.
You connect your Figshare account using a Personal Access Token within the Vinkius platform.
Your AI agent uses the available tools to interpret your request—for instance, finding all files for Article X or listing public collections.
The agent executes the necessary commands and reports back the requested data or confirms the action was taken.
Who is this actually for?
Researchers, academics, and data managers who get frustrated having to context-switch between their publishing platform and their analysis tools. If you spend time manually updating metadata or tracking file statuses across multiple tabs, this MCP is for you.
Quickly create private articles when an experiment finishes, then update the title and description with new results before submitting.
Automate the organization of large data sets by creating multiple projects or collections and listing all associated files for audit purposes.
Query public research outputs across many authors, then retrieve total downloads or views to build usage reports.
What Changes When You Connect
You save time by avoiding manual data entry. Instead of logging into Figshare to change an article's description and then remembering to update the associated project metadata, you simply instruct your agent to handle it all in one go.
Track impact without opening a dashboard. You can ask the MCP for total views or download counts on specific research pieces using get_article_downloads—all through conversational prompts.
Keep drafts and ongoing work separate from published material. Use create_private_article to write and upload files for an experiment before you're ready to make it public, giving you full control over timing.
Organize complex datasets better than folders can. You build structure by listing or creating projects and collections, allowing your agent to search across those boundaries using tools like search_projects.
Update publication details instantly. If a study's scope changes, instead of manually editing the article page, you call update_article to change the title and description immediately.
See it in action
Preparing a paper for submission
A researcher has finished their core analysis files. They ask the agent to create a private article draft, upload all associated raw data using initiate_file_upload, and then update the article description with the final methodology details. The entire process happens without leaving the chat.
Auditing old datasets
A librarian needs to prove usage for a grant report. They ask the agent to list public articles, select five key pieces, and then retrieve the total views and download counts for each using get_article_views and get_article_downloads.
Refactoring an old project
A data manager realizes two related datasets were published separately. They ask the agent to create a new dedicated collection, list all files from the two old articles using list_article_files, and then add those files to the newly created group.
Tracking organizational output
An archivist needs to check if a specific set of core institutional metadata has been updated. They ask for custom field details using get_custom_fields and confirm that all required data points are current before publication.
The honest tradeoffs
Trying to dump everything into one tool call
The user tries to use a single prompt: 'List my articles, upload these files, and update the description for article 123.' This fails because the agent needs distinct instructions for separate actions.
Break it up. First, list the public articles using list_public_articles. Then, separately run initiate_file_upload for the new data set. Finally, call update_article specifying the exact field changes.
Forgetting to check file association
A user uploads a large dataset but doesn't know which article it belongs to, so they just upload it and assume it's linked. The system can't track the provenance.
Before uploading, use list_article_files on the target article ID to verify existing content. Then, when ready, call complete_file_upload for proper linkage.
Over-relying on basic searching
A search query returns too many results because it's too general (e.g., 'climate change'). The user can't narrow down the scope effectively.
Use advanced, targeted searches. For maximum precision, use search_articles or search_collections and pass specific metadata filters.
When It Fits, When It Doesn't
Use this MCP if your workflow involves managing a lifecycle: drafting private work, uploading data, updating metadata, tracking usage metrics (views/downloads), and then finally publishing. It's built for the full scope of academic publishing.
Don’t use it if you only need to retrieve simple lists of public items; basic list_public_articles handles that fine. More importantly, don't expect it to write your research findings—it just manages where and how they are stored. If you just need to perform a single action (like deleting an article), use the dedicated tools like delete_article. It’s best used when the task requires coordination between several distinct operations, such as creating a project and then adding articles to it via create_project and subsequent updates.
Questions you might have
How do I update metadata using the Figshare MCP? (update_article) +
You simply ask the agent to change it. You call update_article and specify which fields—like the title or description—need changing for a given article ID.
Can I upload files using Figshare MCP? (initiate_file_upload) +
Yes, you initiate uploads by calling initiate_file_upload. The process is multi-step; the agent starts the transfer and then needs to use complete_file_upload afterward.
What does list_public_articles do? (list_public_articles) +
This tool retrieves a clean, comprehensive list of every article that has been made public on your Figshare profile for easy review or auditing.
Do I need to use search_articles if I know the ID? (get_article) +
No. If you have a specific Article ID, always use get_article first because it provides all details directly without needing an advanced search query.
Can I create draft work with Figshare MCP? (create_private_article) +
Yes. You can call create_private_article to generate a new, unpublished draft article in your account, letting you prepare content before making it visible.
How do I check an article's impact or usage using `get_article_downloads` or `get_article_views`? +
You retrieve the total download count or view count for a specific article. This lets you track scholarly interest and monitor your publication’s performance metrics without manually checking the Figshare dashboard.
What's the purpose of using `create_collection`? Does it organize my output? +
It allows you to group related articles, datasets, or projects under one umbrella. Think of it as building a curated bibliography or a research portfolio rather than just uploading individual files.
After I run `initiate_file_upload`, how do I finalize the transfer using `complete_file_upload`? +
File uploads require two steps. First, you start the process; then, running complete_file_upload handles the remaining data and makes the file fully live in your Figshare account.
Can I upload files to a Figshare article using this integration? +
Yes. You can use initiate_file_upload to start the process and complete_file_upload once the data transfer is finished. You can also use list_article_files to verify the contents of any article.
How do I create a new private draft for my research? +
Simply ask the agent to use the create_private_article tool. Provide a title and an optional description, and the agent will generate a new private entry in your Figshare account.
Is it possible to organize my articles into projects or collections? +
Absolutely. You can use create_project or create_collection to set up organizational structures, and use list_public_projects or list_public_collections to browse existing ones.
We've already built the connector for Figshare. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 20 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.