How to Use the Europe PMC MCP in Vercel AI SDK

Q: How do I use the Vercel AI SDK to search Europe PMC for articles on CRISPR?

Pass the searcharticles tool to streamText. Your agent will call the tool with a query like { "query": "CRISPR" }, and the AI SDK will stream the results directly into your React components. It's a clean way to use an MCP server without backend complexity.

Q: What's the best way to show grant data from Europe PMC in a Next.js app with the Vercel AI SDK?

Use the searchgrants tool. The results stream back as structured JSON, so you can easily map over them to render a list or a chart showing funding information.

Q: Can I filter my Europe PMC article search by author using the Vercel AI SDK?

Yes. Your agent can use getarticlefields to see available filters and then construct a precise query for searcharticles, like { "query": "AUTH:Kording K" }.

Stream 33M+ life science articles from Europe PMC directly into your UI with the Vercel AI SDK. No more loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Europe PMC MCP to Vercel AI SDK

Create your Vinkius account to connect Europe PMC 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 Europe PMC with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Find Publications in Real-Time

The `search_articles` tool connects your Vercel AI SDK app to the entire Europe PMC database. Your agent can query millions of biomedical and life science articles and stream the results back, one by one. This isn't a simple data dump. Because the AI SDK is built for streaming, you can build UIs where search results appear instantly in your Next.js or Svelte app. It's a much better user experience than waiting for a full list to load.

Track Research Funding

Use the `search_grants` tool to find out who is funding what. Your agent can dig into the Grist API to get details on research grants. It’s a great way to build dashboards for research administrators or analysts. You can show funding trends, connect grants to institutions, and give users a clear picture of the research landscape, all powered by your agent.

Build Dynamic Search Forms

The `get_article_fields` tool lets your agent discover all the available search parameters for articles. It's a simple but powerful utility. Instead of hardcoding search filters, your Vercel app can use this tool to dynamically generate a search form. When Europe PMC adds a new way to filter articles, your UI updates automatically. This MCP server handles the connection for you.

Setup guide

Set up Europe PMC 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 Europe PMC 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 Europe PMC 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 Europe PMC. 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 Europe PMC 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 Europe PMC MCP in Vercel AI SDK

Pass the `search_articles` tool to `streamText`. Your agent will call the tool with a query like `{ "query": "CRISPR" }`, and the AI SDK will stream the results directly into your React components. It's a clean way to use an MCP server without backend complexity.

Use the `search_grants` tool. The results stream back as structured JSON, so you can easily map over them to render a list or a chart showing funding information.

Yes. Your agent can use `get_article_fields` to see available filters and then construct a precise query for `search_articles`, like `{ "query": "AUTH:Kording K" }`.

You get access to article metadata like titles, authors, and abstracts from over 33 million publications. You can also search for research grant information, including funding organizations and award amounts.

Yes, your queries are private. This MCP server processes article and grant searches ephemerally. Vinkius doesn't store your search terms or the results; they're passed from Europe PMC to your AI client and that's it.

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