- BIBLIOGRAPHY
- REPOSITORY
- DATASET
- HUMAN
Short answer
How can I automate research metadata collection?
Your AI uses the CORE Connector to fetch specific article, journal, and repository details directly from open access databases. This allows you to build structured bibliographies without manual searching. You'll get precise metadata for every source you identify.
Where your data lands.
Research outcomes.
The AI organizes the extracted information into these specific outputs.
BIBLIOGRAPHY
Structured citation lists
The AI gathers author names, titles, and publication dates. It formats these into clean lists ready for your papers.
REPOSITORY
Source mapping
Your agent identifies exactly which repository or journal hosted the work. This ensures you know where every piece of data originated.
DATASET
Clean research tables
The AI pulls metadata into a structured format. You can then move this data into spreadsheets or databases for analysis.
HUMAN
Final verification
The AI flags any ambiguous or missing metadata. You step in to check the final citations before you publish or submit.
The workflow
What your AI does when a research task arrives.
The AI moves from a single identifier to a complete metadata profile.
Identify the source
The AI looks up the specific repository or OAI endpoint to find where the research lives.
resolve_oaiLocate the article
Once the source is found, the agent pulls the specific article record you requested.
get_articleExtract journal details
The AI pulls the full publication context, including journal-level metadata.
get_journalMap the repository
The agent confirms the hosting institution or repository details for the record.
get_repository
Try it
Copy these to start.
Use these prompts to trigger the CORE Connector.
Starting points
Swap out the bracketed text with your specific DOI, URL, or journal name.
CORE Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_7PeKa9CanElMqqQ2XoE84ZpBG1HOnxRxZSO8lIZu/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — CORE capabilities are ready to use.
{
"mcpServers": {
"core-open-access-research-mcp": {
"url": "https://edge.vinkius.com/vk_preview_7PeKa9CanElMqqQ2XoE84ZpBG1HOnxRxZSO8lIZu/mcp"
}
}
}Use CORE to get the metadata for this article: [DOI or URL]
Find the journal details for the paper found at [URL]
Identify the repository hosting this research: [DOI]
Build a bibliography from these three articles: [List of URLs]
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect CORE once, then ask.
One click connects the CORE MCP to your preferred client. Your credentials stay encrypted, and you can start pulling data immediately.
Connect CORE to your AIFAQ
How this task behaves.
- 01
Can the AI download the full PDF of the article?
No. The AI only pulls the metadata and descriptive information about the article.
- 02
Will the AI automatically update my existing bibliography files?
No. The AI provides the data to you, but you must manage the actual writing and updating of your files.
- 03
Does it work with any research paper?
It works with any research available through CORE's open access collections.
- 04
Can I use this to find papers that aren't open access?
No. The tool is specifically designed to pull from open access repositories and journals.
- 05
Can the AI fix typos in the original journal metadata?
No. The AI retrieves the data exactly as it is recorded in the source repository.
More questions about CORE? See everything the CORE Connector can do
Connect CORE to Claude, Cursor, ChatGPT & more
