Compatible with every major AI agent and IDE
What is the PubMed Central MCP Server?
Connect your AI agent to PubMed Central (PMC), the world's premier digital archive of biomedical and life sciences journal literature. This server enables deep exploration of millions of open-access articles directly through natural conversation.
What you can do
- Advanced Search — Use
search_articlesto find PMCIDs matching complex queries, including authors, dates, and specific filters. - Full-Text Retrieval — Access complete article content in BioC XML or JSON formats using
get_bioc_articlefor deep analysis. - Citation Analysis — Track the scientific impact of research by finding articles that cite a specific PMID with
get_citing_articles. - Identifier Mapping — Seamlessly convert between PMCIDs, PMIDs, and DOIs using
convert_idsto ensure data consistency. - Metadata Harvesting — Retrieve document summaries, license information, and file locations for Open Access records via
get_article_summaryandget_oa_record.
How it works
- Subscribe to this server
- Provide your NCBI Tool Name and Email (and an optional API Key for higher rate limits)
- Start querying the global repository of medical knowledge from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Researchers & Academics — Instantly find relevant literature and extract data from full-text papers without manual downloading.
- Healthcare Professionals — Quickly verify medical facts and access the latest clinical studies directly from your workspace.
- Data Scientists — Automate the collection of biomedical datasets and citation networks for large-scale analysis.
Built-in capabilities (7)
Convert between article identifiers (PMCID, PMID, DOI)
Get metadata summaries for PMC articles
Retrieve full-text articles via the BioC API
Find PMC articles that cite a specific PubMed ID
Find citation data, license info, and file locations for OA articles
Harvest metadata via the PMC OAI-PMH Service
Search for articles in PubMed Central
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 7 tools from PubMed Central through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries PubMed Central, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
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 Central in OpenAI Agents SDK
PubMed Central and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect PubMed Central to OpenAI Agents SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for PubMed Central in OpenAI Agents SDK
The PubMed Central 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. All 7 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* 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
How Vinkius secures
PubMed Central for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the PubMed Central MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I convert a DOI or PMID into a PMCID for full-text access?
Use the convert_ids tool. Provide a comma-separated list of identifiers, and the agent will return the mapped PMCID, which is required for many other PMC retrieval tools.
Can I retrieve the actual content of an article, not just the abstract?
Yes. If the article is in the Open Access subset, use get_bioc_article with the PMCID. You can specify 'json' or 'xml' format to get the full-text sections.
How can I find which papers have cited a specific study?
Use the get_citing_articles tool by providing the PubMed ID (PMID) of the study. It will return a list of PMC articles that reference that specific work.
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.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
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.
Explore More MCP Servers
View all →
Kaseya
10 toolsManage IT infrastructure, devices, and automation via Kaseya VSA 10.

TheSportsDB Global Sports Database
16 toolsThe definitive sports metadata server — search teams, players, leagues, and live results via AI.

GoFood
12 toolsAutomate GoFood merchant operations — manage outlets, menus, orders, promos, and payments directly from any AI agent.

EPA Envirofacts (Environmental Data)
6 toolsAccess US environmental data including UV forecasts, facility information, and toxic release inventories directly from the EPA.
