How to Use the Figshare MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK handle large file uploads to Figshare?

The SDK runs initiatefileupload to prepare the Figshare storage slot and chunking parameters. It then executes completefileupload once the transfer finishes, verifying the upload status programmatically.

Q: How do I query public research collections using Figshare and the OpenAI Agents SDK?

You pass the listpubliccollections tool to your agent, which retrieves structured JSON containing collection IDs and metadata. The agent then parses this data to find relevant research outputs for your analytical workflows.

Q: Can my OpenAI Agents SDK agent organize Figshare research outputs into distinct groups?

Your agent uses createproject and createcollection to group related research articles. It then calls updatearticle to link individual datasets to those parent containers.

Securely publish and manage research datasets on Figshare using the OpenAI Agents SDK with built-in execution guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect Figshare to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stage Private Articles with OpenAI Agents SDK

The `create_private_article` tool lets your OpenAI Agents SDK system initialize draft records in Figshare without risking premature public exposure. This specific tool sets up the private container, allowing you to apply OpenAI Agents SDK validation guardrails before any files hit the Figshare repository. You then run `initiate_file_upload` and `complete_file_upload` to move the research data directly into the Figshare draft using OpenAI Agents SDK's streamable HTTP transport. The agent checks the metadata quality before finalizing, ensuring your institutional Figshare records stay compliant with open-access policies.

Run Metadata Audits on Your Figshare MCP Server

The `get_custom_fields` tool retrieves Figshare-specific metadata schemas directly into your OpenAI Agents SDK execution environment. Your agent inspects these custom fields to verify that incoming research outputs match your library's strict Figshare cataloging requirements. If any required Figshare fields are missing, the agent uses `update_article` to apply correct metadata tags within the OpenAI Agents SDK workflow. This automated vetting loop prevents messy Figshare records and keeps research discoverable without manual librarian data entry.

Track Dataset Engagement with OpenAI Agents SDK

The `get_article_views` tool pulls raw view counts for any published Figshare DOI, giving your OpenAI Agents SDK telemetry on research impact. Your agent combines this with `get_article_downloads` to build automated Figshare impact reports for department heads. By querying `search_projects` and `search_collections` through the Figshare MCP Server, the agent aggregates these engagement metrics across entire academic departments. The OpenAI dashboard traces these Figshare tool calls, giving you full visibility into how your agents extract and process institutional research statistics.

Setup guide

Set up Figshare MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Figshare tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Figshare tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Figshare tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Figshare Agent",
            instructions="You have access to Figshare tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

The SDK runs `initiate_file_upload` to prepare the Figshare storage slot and chunking parameters. It then executes `complete_file_upload` once the transfer finishes, verifying the upload status programmatically.

Yes, you configure tool access at the Agent constructor level when passing the MCP server endpoint. This prevents the agent from calling destructive tools like `delete_article` while leaving discovery tools active.

You pass the `list_public_collections` tool to your agent, which retrieves structured JSON containing collection IDs and metadata. The agent then parses this data to find relevant research outputs for your analytical workflows.

Your agent uses `create_project` and `create_collection` to group related research articles. It then calls `update_article` to link individual datasets to those parent containers.

The MCP server runs inside a zero-trust V8 sandbox, routing all `create_private_article` and file metadata payloads through secure HTTPS. Your unpublished research datasets and draft metadata remain private until you explicitly trigger a publication workflow.

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