How to Use the PMC Open Access (PubMed Central) MCP in Mastra AI

Q: Can Mastra AI pause a PMC Open Access (PubMed Central) workflow for human review?

Yes. You can set requireToolApproval on tools like oailistrecords. The workflow halts until an admin approves the bulk extraction.

Build resilient biomedical data pipelines in Mastra AI with automatic retries for PubMed Central queries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect PMC Open Access (PubMed Central) MCP to Mastra AI

Create your Vinkius account to connect PMC Open Access (PubMed Central) to Mastra AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup PMC Open Access (PubMed Central) with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Resilient PMC batch queries

The `oai_list_records` tool extracts full OAI records for batches of PMC articles. When you run this through Mastra AI, the framework handles the inevitable rate limits native to bulk OAI-PMH syncing. If the PMC endpoint throttles your request, Mastra's workflow engine kicks in with exponential backoff. Your sync job pauses, waits, and retries the exact same batch without writing custom error handlers.

Conditional ID conversions

The `convert_ids` tool translates manuscript IDs into standard DOIs or PMCIDs. You map out a Mastra workflow that checks for a PMID. If it is missing, the agent branches the logic and calls the tool to fill the gap. Once the ID resolves, the next step in your pipeline triggers `export_citation`. You get perfectly formatted RIS data appended to your database records automatically.

Automated MCP Server discovery

The `oai_identify` tool pings the PMC repository to confirm its base URL and protocol version. It is a quick health check your agent runs before starting a massive data pull. After validating the target, `oa_discover` finds the actual downloadable resources. Mastra handles the MCP transport layer entirely, switching between Streamable HTTP or SSE based on your environment.

Setup guide

Set up PMC Open Access (PubMed Central) 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 PMC Open Access (PubMed Central) 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: "pmc-open-access-pubmed-central-mcp-client",
  servers: {
    "pmc-open-access-pubmed-central-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent PMC Open Access (PubMed Central) 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 PMC (PubMed Central). 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 PMC Open Access (PubMed Central) 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 PMC Open Access (PubMed Central) MCP in Mastra AI

Install @mastra/mcp@latest. Connect the MCP Server by instantiating the MCPClient and passing the Vinkius endpoint URL. Call mcpClient.listTools() and spread the results into your agent's toolkit.

Yes. You can set requireToolApproval on tools like oai_list_records. The workflow halts until an admin approves the bulk extraction.

You build a loop in your Mastra workflow. The agent checks the resumption token from the tool output and triggers the next batch automatically.

You configure timeouts at the Mastra client level. The server processes the request as fast as the upstream PMC API allows.

The MCP Server touches public research article metadata, author names, and abstract text. The ephemeral Vinkius sandbox wipes all session memory the second the workflow completes its task.

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