Plugin

Papers by Ouroboros Apps

Early access

Research-paper search with real citations. It searches OpenAlex, Semantic Scholar, PubMed, Crossref, and arXiv. For researchers, students, and writers who need real citations.

A citation is only as good as the record the API returned. An empty result means those sources didn't return a match, not that the paper doesn't exist.

Server URL

https://papers-mcp.vercel.app/mcp

Connect

Claude: Customize, then Connectors, then Add custom connector. Paste the URL and sign in.
Cursor: add this to ~/.cursor/mcp.json or .cursor/mcp.json, then restart and sign in.
Grok: grok.com/connectors, New Connector, Custom, then the URL.

ChatGPT's directory doesn't list this yet. Use developer mode until it does. That's the early-access route.

{
  "mcpServers": {
    "papers": {
      "url": "https://papers-mcp.vercel.app/mcp"
    }
  }
}

Tools

These names and descriptions are what the server returns from tools/list before you sign in.

search_papers Search peer-reviewed and preprint records by question or keywords. Filters: year_from, year_to, field, open_access, and source (openalex, semantic_scholar, pubmed, crossref, arxiv, or all). Returns only works those APIs returned, each with
get_paper Fetch one paper's title, authors, year, venue, and abstract by DOI, PMID, arXiv id, or OpenAlex work id. Metadata comes from the API that resolved the identifier. If no source returns a record, say so. Do not guess the abstract.
find_related_papers List papers that cite a work (relation cited_by) or papers that work cites (relation references). Every row is an API hit. An empty list means the API returned none, not that none exist.
format_citation Format a real paper in APA, MLA, Chicago author-date, or BibTeX using metadata fetched for the identifier. Titles are kept as the source provided them. Author particles may need a human check because display names are split mechanically. If