How to Use the Figshare MCP in AutoGen

Q: How do AutoGen agents collaborate on Figshare uploads?

You can deploy one agent to run createprivatearticle and another to execute initiatefileupload. This MCP Server lets them communicate via the AutoGen framework to pass article IDs and upload states back and forth.

Q: How do AutoGen agents handle file verification on Figshare?

One agent calls listarticlefiles to retrieve the active file list, while another agent verifies the file sizes. They must agree on the integrity of the upload before running completefileupload.

Let AutoGen agents debate metadata compliance and manage your Figshare uploads automatically via this MCP Server.

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 AutoGen

Create your Vinkius account to connect Figshare to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative metadata curation with AutoGen

The `create_private_article` tool enables your AutoGen agents to draft new research records and collaborate on metadata verification. Your curator agent calls `get_custom_fields` to check for institutional compliance and runs `update_article` before finalizing the upload within the AutoGen conversation.

Multi-agent file staging and verification

The `initiate_file_upload` tool lets your AutoGen agents coordinate and monitor large research dataset transfers. Once the transfer completes, the monitoring agent executes `complete_file_upload` to seal the record and notify the other AutoGen agents.

Automated project organization and review

The `search_articles` tool allows your AutoGen agents to scan incoming research and decide where it belongs. If a matching folder doesn't exist, one agent can run `create_project` while another links the new files, keeping your AutoGen workspace organized.

Setup guide

Set up Figshare MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Figshare tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Figshare_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Figshare data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Figshare_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Figshare data")
    print(result.messages[-1].content)

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 AutoGen

You can deploy one agent to run `create_private_article` and another to execute `initiate_file_upload`. This MCP Server lets them communicate via the AutoGen framework to pass article IDs and upload states back and forth.

Yes, a curator agent can fetch institutional standards with `get_custom_fields` and audit your drafts. The agent can then use `update_article` to apply missing tags or descriptions within your AutoGen workflow.

One agent calls `list_article_files` to retrieve the active file list, while another agent verifies the file sizes. They must agree on the integrity of the upload before running `complete_file_upload`.

If your auditing agents decide a draft is a duplicate or contains errors, they can call `delete_article`. This keeps your MCP workspace clean and prevents accidental publication.

Your scholarly files and private drafts are protected by token-based authentication. The MCP Server executes commands within an isolated V8 sandbox, ensuring your credentials are never exposed during AutoGen execution.

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