Bring Open Access
to OpenAI Agents SDK
Learn how to connect CORE (Open Access Research) to OpenAI Agents SDK and start using 10 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the CORE (Open Access Research) MCP Server?
Connect to CORE, the world's largest aggregator of open access research papers. This MCP server allows your AI agent to search, retrieve, and analyze millions of scholarly articles, journals, and institutional repositories through natural conversation.
What you can do
- Global Search — Search across all CORE resources including articles, journals, and repositories using a single text query.
- Article Retrieval — Fetch full metadata, version history, and direct PDF download links for specific research papers using CORE IDs.
- Journal & Repository Discovery — Search and inspect specific journals by ISSN or explore institutional repositories to find authoritative sources.
- OAI Resolution — Resolve Open Archives Initiative (OAI) identifiers to access original metadata and repository pages.
- Deep Metadata Inspection — Analyze article history and updates to ensure you are working with the latest scientific information.
How it works
- Subscribe to this server
- Enter your CORE API Key
- Start researching directly from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Researchers & Academics — quickly find relevant papers and download PDFs without leaving your writing or coding environment.
- Students — gather citations, explore related research history, and find open access versions of paywalled content.
- Data Scientists — access a massive corpus of open access metadata for literature reviews and scientific data analysis.
Built-in capabilities (10)
Get a specific article by CORE ID
Get the history of an article
Get the PDF download URL for an article
Get a specific journal by ISSN
Get a specific repository by ID
Global search across CORE
Resolve an OAI identifier
Search for articles
Search for journals
Search for repositories
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 10 tools from CORE (Open Access Research) through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries CORE (Open Access Research), 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
CORE (Open Access Research) in OpenAI Agents SDK
CORE (Open Access Research) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect CORE (Open Access Research) 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 CORE (Open Access Research) in OpenAI Agents SDK
The CORE (Open Access Research) 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 10 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
CORE (Open Access Research) for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the CORE (Open Access Research) 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 get the PDF of a specific research article?
Use the get_article_pdf tool with the CORE Article ID. The agent will return the direct download URL for the open access PDF version of the paper.
Can I search for specific journals or repositories?
Yes! You can use search_journals or search_repositories for general text queries, or use get_journal (with an ISSN) and get_repository (with a Repository ID) for direct lookups.
What does the OAI resolution tool do?
The resolve_oai tool takes an OAI identifier (like oai:oro.open.ac.uk:75049) and resolves it to the CORE metadata page or the original repository link, helping you find the source of the research.
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 →
Hubilo
10 toolsManage virtual and hybrid events via Hubilo API.
Beagle Security
10 toolsAutomate security testing via Beagle Security — list projects, start tests, and retrieve results directly from any AI agent.
Paperless-ngx
26 toolsManage your digital archive via Paperless-ngx — search documents, upload files, manage tags, and organize correspondents directly from any AI agent.
Brevo
10 toolsAutomate marketing campaigns via Brevo — send transactional emails, dispatch SMS messages, and manage contacts natively.