Do I need an API key or any registration to use PubMed?

No. PubMed E-utilities are freely accessible to everyone without registration. An optional API key (available at ncbi.nlm.nih.gov) increases your rate limit from 3 to 10 requests per second, but is not required for standard usage.

What types of searches are supported and how can I refine my results?

You can search by keyword, disease name, gene symbol, drug name, author surname, or journal title. Boolean operators (AND, OR, NOT) and field tags like [Title], [Author], and [MeSH Terms] work natively. Example: 'CRISPR AND cancer NOT review' targets original research on CRISPR in oncology.

Can I access full-text articles through this server?

This server returns complete abstracts and metadata for all indexed articles. Full-text access depends on publisher open access policies — articles from PubMed Central (PMC) are freely available. The DOI link provided with each result allows direct navigation to the publisher's page.

PubMed MCP Server for OpenAI Agents SDK 3 tools — connect in under 2 minutes

Name: PubMed
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 3 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect PubMed through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="PubMed Assistant",
            instructions=(
                "You help users interact with PubMed. "
                "You have access to 3 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from PubMed"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About PubMed MCP Server

Connect your AI agent to the National Library of Medicine's PubMed database — the undisputed gold standard for biomedical and life sciences literature worldwide.

The OpenAI Agents SDK auto-discovers all 3 tools from PubMed through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries PubMed, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Literature Search — Find research articles by keyword, disease name, gene symbol, drug, or any biomedical topic across 37M+ indexed articles using powerful boolean operators (AND, OR, NOT)
Full Article Details — Retrieve comprehensive metadata including complete abstracts, all contributing authors, publishing journal, DOI, publication types, and MeSH descriptors for any article by PMID
Citation Tracking — Discover which subsequent papers cite a specific article to trace the impact chain and follow the evolution of a research topic over time

The PubMed MCP Server exposes 3 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect PubMed to OpenAI Agents SDK via MCP

Follow these steps to integrate the PubMed MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 3 tools from PubMed

Why Use OpenAI Agents SDK with the PubMed MCP Server

OpenAI Agents SDK provides unique advantages when paired with PubMed through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

PubMed + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the PubMed MCP Server delivers measurable value.

Automated workflows: build agents that query PubMed, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries PubMed, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through PubMed tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query PubMed to resolve tickets, look up records, and update statuses without human intervention

PubMed MCP Tools for OpenAI Agents SDK (3)

These 3 tools become available when you connect PubMed to OpenAI Agents SDK via MCP:

get_pubmed_article

Get full details of a PubMed article by its PMID

get_pubmed_citations

Useful for tracing the impact of a paper and finding follow-up research. Find articles that cite a specific PubMed paper

search_pubmed

Returns titles, authors, journals, abstracts, DOIs, and MeSH terms. Supports boolean operators: AND, OR, NOT. Search PubMed for biomedical and life sciences research articles

Example Prompts for PubMed in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with PubMed immediately.

"Find recent research on CRISPR gene therapy for sickle cell disease."

"Get complete details for PubMed article PMID 33782455."

"Which papers cite the original CRISPR-Cas9 paper? Show me the top citing articles."

Troubleshooting PubMed MCP Server with OpenAI Agents SDK

Common issues when connecting PubMed to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

PubMed + OpenAI Agents SDK FAQ

Common questions about integrating PubMed MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.