An astronaut overseeing a futuristic data hub

Connect Figshare to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Handle your scholarly data without leaving your AI workspace.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 20 capabilities

We ship only the actions that matter.

Capability set01 / 05

01-04

4 capabilities in this set.

Part of 20 available through Figshare.

  1. 01

    Create private article

    This capability creates a new private article in your Figshare account. Use it to start a new research entry that isn't public yet.

  2. 02

    Create project

    This capability sets up a new project. It helps you group related research activities together.

  3. 03

    Initiate file upload

    This capability starts the file upload process for a specific article. It is the first step in getting your data into the repository.

  4. 04

    List article files

    This capability retrieves a list of all files attached to a specific article. Use it to verify what data is currently stored.

Capability set02 / 05

05-08

4 capabilities in this set.

Part of 20 available through Figshare.

  1. 05

    Search projects

    This capability performs an advanced search across your existing projects. It helps you find specific research groupings quickly.

  2. 06

    Update article

    This capability modifies the details of an existing article. You can use it to change descriptions or other core information.

  3. 07

    Create collection

    This capability generates a new public collection. It is useful for organizing multiple articles into a single themed group.

  4. 08

    Delete article

    This capability removes an article from your account. Use it when a record is no longer needed.

Capability set03 / 05

09-12

4 capabilities in this set.

Part of 20 available through Figshare.

  1. 09

    Get custom fields

    This capability fetches the custom metadata fields required by your specific institution. It ensures your data meets local standards.

  2. 10

    Get file details

    This capability provides specific information about a single file. It is helpful for checking file sizes or formats.

  3. 11

    Get article

    This capability pulls all the details for a specific article. Use it to get a full view of a single research entry.

  4. 12

    Get article downloads

    This capability retrieves the total download count for an article. It lets you track how often your data is being used.

Capability set04 / 05

13-16

4 capabilities in this set.

Part of 20 available through Figshare.

  1. 13

    Get article views

    This capability gets the total number of views for an article. Use it to monitor the visibility of your research.

  2. 14

    Get hrfeed upload

    This capability retrieves details regarding an HR feed upload. It is used for specific institutional data workflows.

  3. 15

    List public articles

    This capability shows a list of articles that are currently public. Use it to audit what is visible to the world.

  4. 16

    List public collections

    This capability lists all public collections in the repository. It helps you browse shared research groupings.

Capability set05 / 05

17-20

4 capabilities in this set.

Part of 20 available through Figshare.

  1. 17

    List public projects

    This capability displays public projects. Use it to see what research groups are openly available.

  2. 18

    Search articles

    This capability searches through articles using advanced criteria. It is the fastest way to find specific research papers or datasets.

  3. 19

    Search collections

    This capability searches for specific collections. Use it to find themed groupings of research.

  4. 20

    Complete file upload

    This capability finalizes a file upload. It tells the system that the data transfer is finished.

Real work

What teams actually run

01

Rapid Dataset Upload

A researcher tells their agent to start an upload for a new experiment, handling the file transfer through the chat.

02

Metadata Auditing

A librarian asks the agent to list all public articles to check if descriptions meet institutional standards.

03

Impact Monitoring

An academic asks for the download counts of their latest publication to see how much it is being cited or used.

04

Project Organization

A data manager uses the agent to create a new collection to group several related datasets together.

Automate a task

Put Figshare to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Figshare works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Figshare to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1046ms average. Fast in production.

Figshare is checked daily against the live service.

Daily averagePeak 1189ms
Oct 3Today
Fastest day
773ms
Slowest day
1189ms
14-day trend
Stable-4%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 20 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Figshare, so you can see the experience inside your AI.

It does not authenticate your account with Figshare. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Figshare Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_U4BwwHBluBnS2piUjlNrvdO2vrPNTpOy41PYnSxz/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Figshare capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "figshare-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_U4BwwHBluBnS2piUjlNrvdO2vrPNTpOy41PYnSxz/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Figshare in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Figshare owners hand off.

This MCP is built for professionals managing scholarly outputs and institutional data repositories.

  • 01

    Researchers

    They use the agent to upload datasets and update article descriptions without leaving their writing environment.

  • 02

    Data Managers

    They automate the organization of large collections and projects across repositories.

  • 03

    Librarians

    They query public research and manage metadata updates for institutional compliance.

FAQ

Questions Figshare owners ask.

  • 01

    How do I connect my Figshare account?

    You subscribe to the MCP on Vinkius and then enter your Figshare Personal Access Token. Once connected, your AI client can immediately start using the capabilities.

  • 02

    Which AI clients can I use with this MCP?

    You can use any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 03

    Can I upload large files through my AI agent?

    Yes. The MCP includes capabilities to initiate multi-part S3 uploads, making it possible to handle large research datasets.

  • 04

    Is my data secure?

    The MCP uses your Figshare Personal Access Token to perform actions, meaning it operates within the permissions you have already established in your Figshare account.

  • 05

    Can I manage private articles?

    Yes. You can create, update, and delete private articles that are not visible to the public.

  • 06

    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.

  • 07

    How do I create a new private draft for my research?

    Simply ask the agent to use the create_private_article capability. Provide a title and an optional description, and the agent will generate a new private entry in your Figshare account.

  • 08

    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.

Connect Figshare to Claude, Cursor, ChatGPT & more