How to Use the Figshare MCP in VS Code Copilot

Q: Can VS Code Copilot help me audit metadata on Figshare?

Yes, your agent can run getarticle to retrieve the complete metadata payload of any record. It then compares this data against your local schema definitions or institutional rules. If it finds discrepancies, it can automatically correct them using updatearticle.

Q: How does VS Code Copilot track research impact on Figshare?

The agent calls getarticleviews and getarticledownloads to fetch live metrics directly into your terminal or chat window. This lets your engineering team build automated reports or dashboards using real-time repository statistics. You do not need to build custom API scrapers to get this data.

Q: Can I manage collaborative projects using this extension?

Yes, you can organize shared workspaces. The agent uses createproject to set up new collaborative environments and searchprojects to find existing ones. This makes it easy to manage group research outputs directly from your editor.

Equip your engineering team to manage Figshare research repositories directly within VS Code Copilot.

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 VS Code Copilot

Create your Vinkius account to connect Figshare to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Standardize Figshare repository management in VS Code Copilot

This Figshare MCP Server enables team-wide metadata management and file staging directly inside your shared editor. By committing a configuration file to your repository, every developer on your team instantly gains access to tools like `create_private_article`. Your agent uses `get_custom_fields` to pull down institutional metadata requirements, ensuring all team members adhere to identical curation standards. Catching errors early eliminates manual cataloging errors before datasets are even uploaded.

Automate bulk file staging and verification

The Figshare MCP Server lets VS Code Copilot handle complex multi-step file uploads programmatically. Your agent initiates the pipeline using `initiate_file_upload` and monitors the transmission of raw research data. After verifying the integrity of the uploaded parts, the agent calls `complete_file_upload` to finalize the record. Your team can now stage entire directories of scientific outputs without leaving the active workspace.

Search and organize institutional projects

This Figshare MCP Server allows VS Code Copilot to query, audit, and organize your institution's public and private research. Your agent runs `search_projects` and `search_collections` to locate specific collaborative spaces or curated datasets. If project structures need adjustment, the agent calls `create_project` or `create_collection` to group outputs correctly. Managing resources this way keeps your institutional data clean and discoverable without requiring manual web interface navigation.

Setup guide

Set up Figshare MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Figshare MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Figshare tools listed. Try asking: "List my recent Figshare transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

Create a .vscode/mcp.json file in your project root and commit it to your Git repository. Once your team members open the project in VS Code 1.96+ with Copilot, the tools will load automatically. Each developer just needs to provide their own personal API token to authenticate.

Yes, your agent can run `get_article` to retrieve the complete metadata payload of any record. It then compares this data against your local schema definitions or institutional rules. If it finds discrepancies, it can automatically correct them using `update_article`.

The agent calls `get_article_views` and `get_article_downloads` to fetch live metrics directly into your terminal or chat window. This lets your engineering team build automated reports or dashboards using real-time repository statistics. You do not need to build custom API scrapers to get this data.

Yes, you can organize shared workspaces. The agent uses `create_project` to set up new collaborative environments and `search_projects` to find existing ones. This makes it easy to manage group research outputs directly from your editor.

No, all file contents and metadata payloads are transmitted directly between your local VS Code environment and the repository API. Vinkius secures this connection using enterprise-grade ephemeral sandboxing. Your raw scientific datasets and draft metadata are never stored or inspected by external servers.

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