How to Use the CORE (Open Access Research) MCP in Vercel AI SDK

Q: Can Vercel AI SDK stream PDF links from CORE (Open Access Research)?

Yes, your agent uses getarticlepdf to pull the direct download link. The Vercel AI SDK streams this URL to your React component, allowing you to render an iframe or download button immediately.

Q: What happens when an OAI identifier is unresolved?

The resolveoai tool returns an error payload which your SDK client catches in the tool execution block. You can then instruct the agent to fall back to globalsearch to find the correct paper.

Stream open academic research directly into your Next.js frontend using Vercel AI SDK and the CORE 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 CORE (Open Access Research) MCP to Vercel AI SDK

Create your Vinkius account to connect CORE (Open Access Research) 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 CORE (Open Access Research) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Academic Search in Vercel AI SDK

This MCP Server exposes `search_articles` to let your React frontends query millions of open-access papers without waiting for a full page load. The Vercel AI SDK handles the SSE connection, piping raw metadata straight to your UI components. You pass the tools array from `mcpClient.tools()` to `streamText`. When the user types a query, the agent calls `search_journals` or `search_repositories` and renders the matching academic records on screen instantly.

Direct PDF and Repository Discovery

The `get_article_pdf` tool resolves raw CORE IDs into direct download links so your application can render papers in real-time. By connecting this MCP tool to your Vercel AI SDK setup, your agent fetches verified open-access PDFs instantly. Behind the scenes, the server resolves OAI identifiers using `resolve_oai` to verify paper origins. Your users get direct access to the source document without manual search steps.

Tracking Paper Updates on the Edge

The `get_article_history` tool pulls the modification timeline for any paper in the CORE database. Running this on Vercel Edge Functions gives you low-latency updates when tracking academic revisions. Your AI client triggers `get_article` to pull the latest metadata schema. This keeps your local database in sync with the live CORE repository.

Setup guide

Set up CORE (Open Access Research) 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 CORE (Open Access Research) 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 CORE (Open Access Research) 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 CORE. 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 CORE (Open Access Research) 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 CORE (Open Access Research) MCP in Vercel AI SDK

You initialize the MCP client in your Next.js route handler and pass the tools directly to `streamText`. The agent automatically selects `search_articles` to query the CORE API based on the user's prompt.

Yes, your agent uses `get_article_pdf` to pull the direct download link. The Vercel AI SDK streams this URL to your React component, allowing you to render an iframe or download button immediately.

The Vinkius platform manages the connection pooling and authentication for the CORE API endpoint. Your SDK client only needs to call `mcpClient.close()` when the edge execution finishes to prevent orphaned connections.

The `resolve_oai` tool returns an error payload which your SDK client catches in the tool execution block. You can then instruct the agent to fall back to `global_search` to find the correct paper.

Vinkius runs this MCP Server in a zero-trust, ephemeral V8 isolate sandbox. Your search queries, CORE IDs, and retrieved PDF metadata are never cached or stored on our servers.

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