How to Use the Figshare MCP in Cursor

Q: How does Cursor handle private Figshare articles?

The agent reads and modifies private drafts using createprivatearticle and updatearticle. It uses your local API token to authenticate these requests securely. Your private research drafts remain hidden from the public index until you manually publish them.

Write code that interacts with Figshare and manage research datasets directly inside the Cursor editor.

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 Cursor

Create your Vinkius account to connect Figshare to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Write code using live Figshare API responses in Cursor

This Figshare MCP Server allows Cursor to fetch live repository data while you write your data-processing scripts. Your agent calls `get_article` or `list_article_files` to retrieve real payloads, allowing it to generate accurate parsing code. You do not have to write code against outdated documentation or mock schemas anymore. By running `get_custom_fields`, the agent inspects your institution's specific metadata constraints directly within the editor. Validating your inputs first ensures your automated ingest scripts match repository requirements before you run them.

Manage dataset uploads from your coding workspace

The Figshare MCP Server lets Cursor manage file staging without switching to a web browser. Your agent initiates the upload process via `initiate_file_upload` and tracks the progress of each file chunk. Once the transfer completes, the agent runs `complete_file_upload` to link the raw files to your draft. Now you can write, test, and execute your dataset upload pipeline in a single environment.

Manage projects and collections from the editor

This Figshare MCP Server lets your Cursor agent organize research outputs into structured containers. The agent calls `create_project` to establish collaborative workspaces or `create_collection` to group related datasets together. If you need to update metadata or clean up drafts, the agent executes `update_article` or `delete_article` based on your codebase structure. Your institutional repository stays organized while you focus on writing your analysis code.

Setup guide

Set up Figshare MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Figshare MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Figshare transactions." If the MCP tools are loaded correctly, Cursor will call the Figshare tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

Add the server details to your local .cursor/mcp.json file or global settings. Include your authentication token as an environment variable so the agent can access your account. Cursor will automatically load the tools, enabling immediate use of functions like `create_private_article` in chat.

Yes, Cursor uses the live tools to verify API behavior in real time. The agent can run `initiate_file_upload` to understand the exact payload structure, then write a Python or Bash script that automates your lab's data pipeline. This eliminates guesswork when writing integration code.

The agent reads and modifies private drafts using `create_private_article` and `update_article`. It uses your local API token to authenticate these requests securely. Your private research drafts remain hidden from the public index until you manually publish them.

Yes, you can check performance metrics directly in your workspace. Your agent calls `get_article_downloads` and `get_article_views` to pull live statistics. This lets you monitor the reach of your published datasets without leaving your development environment.

All data transfers and metadata operations run through local stdio transport or secure Vinkius sandboxes. Your API keys and research files are never exposed to external telemetry. This ensures your unpublished intellectual property remains strictly within your secure local environment.

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