Paper Search

Academic paper discovery and retrieval in this harness runs through the mcp__paper-search__* tools (the paper-search-mcp MCP server). Do not run the paper-search CLI or hand-write API requests — use these tools.

Core tools

• mcp__paper-search__search_papers — multi-source concurrent search with deduplication and DOI backfill. Prefer it for broad queries; one call covers many sources at once.
• mcp__paper-search__download_with_fallback — OA-first PDF download with a source-native → repository → Unpaywall fallback chain.
• mcp__paper-search__search_unpaywall — DOI-centric open-access metadata lookup.

Source-specific tools

Per source the pattern is search_<source> / download_<source> / read_<source>_paper, with availability varying by source. Sources: arxiv, pubmed, biorxiv, medrxiv, iacr, semantic, crossref, openalex, pmc, core, europepmc, dblp, openaire, citeseerx, doaj, base, zenodo, hal, ssrn, openreview, google_scholar. ACM search is available without an API key. IEEE tools require PAPER_SEARCH_MCP_IEEE_API_KEY. Discover the current tool list rather than assuming every source supports full text.

Web of Science (search_wos) and Scopus (search_scopus, read_scopus_paper) require runtime keys and explicit source selection; default/all searches never include them. Scopus full-text retrieval requires explicit full_text=true; respect its full_text, abstract_only, or unavailable status. Do not describe an abstract or metadata record as retrieved full text.

get_citing_papers and get_referenced_papers provide bounded one-hop OpenAlex lookups from a DOI or OpenAlex ID. Search caching is disabled by default; enabling it persists queries and public results and is an operator choice. Use get_search_cache_status to inspect it and clear_search_cache only when the user asks to remove cached results. Clearing does not remove downloaded PDFs.

For speed, prefer a targeted set (search_arxiv, search_semantic, search_crossref) over multi-source search when the field is clear.

Workflow

1. Search: search_papers for broad coverage, search_<source> for targeted queries.
2. Present results as a table: title, authors, year, source, DOI/URL.
3. Full text: read_<source>_paper; PDF: download_<source> or download_with_fallback, then report the saved path.

Notes

• Many public sources work without API keys; optional keys (Semantic Scholar, CORE, Unpaywall email, …) live in ~/.config/paper-search-mcp/.env and are loaded by the server automatically.
• Google Scholar and SSRN can be bot-blocked upstream; fall back to other sources rather than retrying.