How to Use the Figshare MCP in Vercel AI SDK

Q: How do I search Figshare datasets using Vercel AI SDK?

You instantiate the MCP client and pass the searcharticles tool to your agent's tool set. The agent then executes the query and returns the results to your stream.

Q: Can Vercel AI SDK handle Figshare file uploads?

Yes, you chain initiatefileupload and completefileupload within your agent's execution flow. This manages the multi-step protocol required by the repository.

Q: How do I list collections via Figshare and Vercel AI SDK?

You invoke listpubliccollections through the MCP interface. The results are returned as a JSON array that you can map directly to your components.

Stream research data from Figshare directly into your Vercel AI SDK frontends for real-time, interactive data visualization.

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 Vercel AI SDK

Create your Vinkius account to connect Figshare to Vercel AI 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live data streaming in Vercel AI SDK

Feed your UI with live repository data by hooking the Figshare MCP server into your edge functions. Your users see dataset details populate as the AI agent fetches them using `list_public_articles` and `get_article`. Stop waiting for static page loads. By piping tool outputs directly into your stream, you bridge the gap between heavy academic repositories and responsive web interfaces.

Automated private article management

Handle sensitive research drafts without leaving your TypeScript environment. You can trigger `create_private_article` and `initiate_file_upload` to stage new datasets for peer review. Your application manages the handoff from local research to the repository. The AI handles the API handshake, ensuring your metadata stays consistent throughout the upload process.

Query institutional metadata fields

Filter research outputs precisely by tapping into custom institutional fields. Use `get_custom_fields` to align your app's search parameters with the specific tagging requirements of your university. This ensures that data surfaced by your agent actually matches the schema your librarians expect. It keeps your application compliant without manual mapping.

Setup guide

Set up Figshare MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Figshare tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Figshare transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

You instantiate the MCP client and pass the `search_articles` tool to your agent's tool set. The agent then executes the query and returns the results to your stream.

Yes, you chain `initiate_file_upload` and `complete_file_upload` within your agent's execution flow. This manages the multi-step protocol required by the repository.

The server uses token-based authentication for every request. You manage your secrets in your environment variables, keeping sensitive research data isolated from the client-side code.

You invoke `list_public_collections` through the MCP interface. The results are returned as a JSON array that you can map directly to your components.

Access is restricted by your API token, which defines the scope of what the server can see. The system treats every record as private unless explicitly marked otherwise, ensuring your unpublished datasets remain invisible to unauthorized agents.

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