How to Use the Figshare MCP in CrewAI

Q: Can CrewAI agents automate private dataset curation on Figshare?

Yes, your CrewAI agents can use createprivatearticle to draft records and keep them private while they run validation checks. Once your CrewAI curation crew verifies the metadata, they can execute updatearticle to prepare the dataset for public release.

Q: How do CrewAI agents handle multi-step file uploads to Figshare?

Your CrewAI agents coordinate the upload by first calling initiatefileupload to get the storage endpoints, uploading the raw data parts, and then executing completefileupload to finalize the Figshare record. This multi-agent coordination ensures large research files are uploaded reliably without stalling.

Give your CrewAI agents direct access to Figshare to publish research, upload datasets, and manage collections autonomously.

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 CrewAI

Create your Vinkius account to connect Figshare to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate academic dataset uploads with CrewAI

The Figshare MCP Server lets your CrewAI research agents draft records and stage files using `create_private_article` and `initiate_file_upload` directly. While one CrewAI agent drafts the metadata, a partner agent executes the multi-step Figshare file upload sequence. This setup replaces manual browser uploads, letting CrewAI automate the tedious academic dataset ingestion workflow. By splitting the ingestion work between specialized CrewAI agents, you ensure that datasets are uploaded securely and indexed immediately in your Figshare repository.

Validate metadata before publishing via MCP Server

By calling `get_custom_fields` and `update_article`, your CrewAI agents can audit and enrich metadata fields to meet strict institutional standards before publishing. A specialized CrewAI librarian agent can pull the required custom schema and update the Figshare article properties automatically. This multi-agent CrewAI workflow ensures no incomplete or poorly tagged datasets are published to your public Figshare portal. Your CrewAI agents cross-reference local research files and apply the correct academic tags before approving any public Figshare release.

Track dataset citations and views with CrewAI agents

Using `get_article_views` and `get_article_downloads` allows your CrewAI analyst agents to monitor research impact and compile download metrics autonomously. You can task a CrewAI reporter agent with scanning your Figshare repository and compiling impact statistics for your annual grant reports. These agents can also run `search_articles` to find related Figshare outputs. This helps your CrewAI research crew build automated literature reviews and map citation networks.

Setup guide

Set up Figshare MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Figshare tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Figshare Analyst",
    goal="Access and analyze Figshare data via MCP.",
    backstory="Expert analyst with direct Figshare access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Figshare transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Figshare Analyst",
        goal="Access and analyze Figshare data via MCP.",
        backstory="Expert analyst with direct Figshare access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Figshare transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You simply pass the Vinkius-managed Figshare MCP server URL directly into your CrewAI agent configuration using the `mcps` parameter. This gives your entire crew of agents instant access to Figshare tools like `create_project` and `create_collection` without manual API integration.

Yes, your CrewAI agents can use `create_private_article` to draft records and keep them private while they run validation checks. Once your CrewAI curation crew verifies the metadata, they can execute `update_article` to prepare the dataset for public release.

Your CrewAI agents coordinate the upload by first calling `initiate_file_upload` to get the storage endpoints, uploading the raw data parts, and then executing `complete_file_upload` to finalize the Figshare record. This multi-agent coordination ensures large research files are uploaded reliably without stalling.

Yes, your CrewAI agents can organize research outputs by using `create_collection` and `create_project` to group related datasets together. This allows your CrewAI research crew to automatically build curated, thematic collections on Figshare based on project metadata.

Vinkius hosts the Figshare MCP server in a secure, isolated V8 sandbox, meaning your API tokens and research datasets are never exposed to other users. Your CrewAI agents communicate through an ephemeral, zero-trust connection, ensuring your private scholarly outputs remain completely secure during automated uploads.

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