How to Use the Figshare MCP in Claude

Q: How do I connect Claude Desktop to my Figshare account?

Add the server configuration to your local claudedesktopconfig.json file under the mcpServers key. Provide your personal API token in the environment variables to authorize the connection. Once you restart Claude Desktop, you can instantly run tools like listpublicarticles directly from the chat input.

Q: Can Claude Desktop upload multi-gigabyte datasets to Figshare?

Yes, your agent handles large files by running initiatefileupload to split the file into manageable parts. It then tracks the upload progress and calls completefileupload to seal the dataset. This keeps your local Claude Desktop app responsive during heavy transfers.

Q: How does Claude Desktop search for existing Figshare projects?

The agent uses the searchprojects tool to query the public database based on your keywords or custom metadata fields. It returns a structured JSON list of matching projects directly in your chat. You can then ask the agent to inspect specific items using getarticle.

Q: Can I delete a published paper using this tool?

No, you can only delete drafts. The agent uses deletearticle to remove private drafts, but published research is permanent on the platform. To modify public records, you must update their metadata instead.

Publish research papers and manage large datasets on Figshare directly from Claude Desktop without leaving your local environment.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Figshare MCP to Claude Desktop

Create your Vinkius account to connect Figshare to Claude Desktop 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 Figshare with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate academic file staging in Claude Desktop

This Figshare MCP Server lets Claude Desktop stage and upload large scientific datasets directly from your machine. Your agent initiates the transfer by calling `initiate_file_upload` and registers the local files to a specific research node. You do not have to copy-paste paths or manually drag files into a browser window anymore. Once the chunks are processed, your agent executes `complete_file_upload` to finalize the record. The final step moves your raw research data from your local storage to your institutional repository with zero manual clicks.

Manage draft metadata and private articles

The Figshare MCP Server exposes tools to build and edit your research records before they go public. Your agent uses `create_private_article` to set up a draft and then applies institutional schema by running `get_custom_fields`. If you need to change authors, categories, or funding details, the agent updates the record via `update_article`. This workflow keeps your draft private until your library curators approve the submission.

Track repository impact and search collections

This Figshare MCP Server lets your Claude Desktop client monitor citation metrics and search external academic work. The agent calls `get_article_views` and `get_article_downloads` to pull real-time impact numbers into your workspace. For literature reviews, the agent runs `search_articles` or `search_projects` to find related work. Grouping these discovered papers into structured collections via `create_collection` speeds up your bibliography building.

Setup guide

Set up Figshare MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

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.
3

Start a conversation

Open a new chat. The Figshare MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Figshare MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under figshare-mcp.

json

{
  "mcpServers": {
    "figshare-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Figshare 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 Figshare MCP in Claude Desktop

Add the server configuration to your local claude_desktop_config.json file under the mcpServers key. Provide your personal API token in the environment variables to authorize the connection. Once you restart Claude Desktop, you can instantly run tools like `list_public_articles` directly from the chat input.

Yes, your agent handles large files by running `initiate_file_upload` to split the file into manageable parts. It then tracks the upload progress and calls `complete_file_upload` to seal the dataset. This keeps your local Claude Desktop app responsive during heavy transfers.

The agent uses the `search_projects` tool to query the public database based on your keywords or custom metadata fields. It returns a structured JSON list of matching projects directly in your chat. You can then ask the agent to inspect specific items using `get_article`.

No, you can only delete drafts. The agent uses `delete_article` to remove private drafts, but published research is permanent on the platform. To modify public records, you must update their metadata instead.

Your research files and metadata stay private because Vinkius runs this MCP Server in an isolated, zero-trust sandbox. The server only communicates with the official API using your local credentials. No draft content or institutional project details are ever cached or shared with third parties.

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