How to Use the Europe PMC MCP in Mastra AI

Q: How can I build a Mastra AI workflow to find Europe PMC articles and then notify me?

Create a two-step workflow. The first step uses the searcharticles tool to find papers. The second step takes the output and uses a different tool to send you the results. Mastra AI makes chaining MCP tool calls like this straightforward.

Q: Can Mastra AI handle errors when searching for grants in Europe PMC?

Yes, that's what it's for. You can wrap your searchgrants tool call in a retry block within your Mastra AI agent definition. The framework handles the backoff and error checking.

Q: My Mastra AI agent needs to search Europe PMC using a specific field. How does it know what fields are valid?

Your agent should call the getarticlefields tool first. This gives it an up-to-date list of all possible fields, preventing errors from using an invalid or deprecated parameter.

Build failure-proof workflows with Europe PMC data using Mastra AI. Automatically retry searches and handle API errors gracefully.

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 Mastra AI

Create your Vinkius account to connect Europe PMC to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Scientific Literature Reviews

The `search_articles` tool is the core of your research automation. A Mastra AI agent can run a query, get the results, and then pass them to another step in your workflow for analysis. Here's the key: Mastra's workflow engine adds a layer of reliability. If a call to `search_articles` fails because of a network blip or rate limit, your agent can be configured to retry automatically. Your research jobs won't fail because of transient errors.

Build Resilient Grant Tracking Systems

Use the `search_grants` tool to build automated systems that monitor research funding. Your agent can periodically check for new grants matching specific criteria, like a particular institution or field of study. With Mastra AI, you can build conditional logic around the data. For example: if `search_grants` finds a new grant over $1M, then trigger a notification. This is the kind of logic an MCP-powered agent excels at.

Your Mastra AI Agent Knows the API

The `get_article_fields` tool lets your agent programmatically discover how to query the articles endpoint. It's a simple lookup that returns all valid search fields. This makes your automations more robust. Instead of a developer hard-coding API parameters, your Mastra agent can use this tool to construct valid queries on its own. This MCP server keeps your agent in sync.

Setup guide

Set up Europe PMC MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Europe PMC tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "europe-pmc-mcp-client",
  servers: {
    "europe-pmc-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Europe PMC Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Europe PMC tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Europe PMC transactions"
);
console.log(result.text);

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 Mastra AI

Create a two-step workflow. The first step uses the `search_articles` tool to find papers. The second step takes the output and uses a different tool to send you the results. Mastra AI makes chaining MCP tool calls like this straightforward.

Yes, that's what it's for. You can wrap your `search_grants` tool call in a retry block within your Mastra AI agent definition. The framework handles the backoff and error checking.

Your agent should call the `get_article_fields` tool first. This gives it an up-to-date list of all possible fields, preventing errors from using an invalid or deprecated parameter.

No. The Vinkius MCP server handles the connection to Europe PMC's public APIs. You just need your single Vinkius endpoint token to connect your agent.

All data is transient. When your Mastra AI agent queries for publication or grant information, this server forwards the request and streams the response back. Nothing is logged or stored on our side.

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