How to Use the Figshare MCP in Google ADK

Q: How does Google ADK authenticate with the Figshare MCP Server?

You configure the McpToolset with your Vinkius HTTP endpoint and security token. The Google ADK handles the transport layer, exposing tools like getarticle directly to your Gemini model.

Q: Can I use Google ADK to track citation and download metrics from Figshare?

Yes, your agent calls getarticledownloads and getarticleviews to retrieve raw engagement metrics. You can then stream these metrics directly into BigQuery for institutional reporting.

Q: How does the Gemini long-context window interact with Figshare search results in Google ADK?

The searcharticles tool returns structured metadata that Google ADK feeds into Gemini's context window. This allows the model to analyze hundreds of dataset descriptions at once to find hidden research trends.

Q: Can the Google ADK agent delete accidental Figshare uploads?

The agent can call deletearticle using the specific article ID if an upload fails validation. You should restrict this tool in your ADK configuration to prevent accidental deletions of valid research.

Q: Where is my Figshare research metadata stored when using this MCP server with Google ADK?

All research metadata and article details processed by getarticle are handled in-memory within Vinkius's ephemeral sandboxes. No scholarly data is cached or stored permanently on the MCP server.

Connect Figshare to your Gemini models using Google ADK to analyze and organize massive research datasets.

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 Google ADK

Create your Vinkius account to connect Figshare to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search and Ingest Figshare Outputs with Google ADK

The `search_articles` tool queries the Figshare repository to extract specific public research datasets directly into your Google ADK environment. This tool feeds structured Figshare data directly into the Gemini model's long-context window, letting you analyze thousands of research papers simultaneously. Your agent can also call `list_public_projects` and `search_projects` to map out collaborative Figshare research networks. The Google ADK integrates these outputs with your existing Vertex AI pipelines for advanced semantic clustering of Figshare data.

Bulk Upload and Organize via Google ADK MCP Server

The `create_project` tool builds collaborative workspaces in Figshare directly from your Google ADK cloud environment. Your agent can initiate these Figshare projects to group related datasets, then use `create_collection` to categorize them for public release. To populate these projects, the agent runs `initiate_file_upload` and `complete_file_upload` to transfer files from Google Cloud Storage to Figshare. This automation bridges the gap between your cloud data lakes and your public Figshare institutional repository.

Audit Figshare Metadata and HR Feeds

The `get_hrfeed_upload` tool retrieves organizational data to verify that Figshare dataset authors match active institutional records. Your Google ADK agent checks this feed against BigQuery tables to ensure accurate authorship attribution across all published outputs. If discrepancies are found, the Google ADK agent calls `update_article` to correct Figshare author metadata before the record goes public. This process keeps your institution's Figshare reporting clean and compliant with federal open-access mandates.

Setup guide

Set up Figshare MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Figshare tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Figshare_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Figshare tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You configure the `McpToolset` with your Vinkius HTTP endpoint and security token. The Google ADK handles the transport layer, exposing tools like `get_article` directly to your Gemini model.

Yes, your agent calls `get_article_downloads` and `get_article_views` to retrieve raw engagement metrics. You can then stream these metrics directly into BigQuery for institutional reporting.

The `search_articles` tool returns structured metadata that Google ADK feeds into Gemini's context window. This allows the model to analyze hundreds of dataset descriptions at once to find hidden research trends.

The agent can call `delete_article` using the specific article ID if an upload fails validation. You should restrict this tool in your ADK configuration to prevent accidental deletions of valid research.

All research metadata and article details processed by `get_article` are handled in-memory within Vinkius's ephemeral sandboxes. No scholarly data is cached or stored permanently on the MCP server.

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