cern-inspire-mcp-server MCP Server

Export INSPIRE-HEP's citation entries for the papers a literature query selects, as BibTeX or LaTeX \bibitem entries (EU or US style), keyed by INSPIRE texkeys and ready to paste into a bibliography. Name specific papers with "recid:451647 or arxiv:1207.7214 or doi:10.1016/…", or export a topic, author, or citing set with any query cern_inspire_search_literature accepts. Up to 50 entries per page; page through larger sets (only the first 10,000 matches are reachable). Entries are INSPIRE's verbatim text (long author lists arrive abbreviated as "First, Name and others").

Compute INSPIRE-HEP's citation summary for one author or for any literature query: h-index, citation totals, average citations per paper, and paper counts per citation bucket (0, 1–9, 10–49, 50–99, 100–249, 250–499, 500+), each for all citeable papers and for published papers, plus citations received per year. Pass exactly one of author (a BAI, ORCID, INSPIRE ID, or author recid — resolve a name with cern_inspire_search_authors first) or query (any INSPIRE literature query: a topic, collaboration, institution, or "a <BAI>"). Document type and subject filters narrow every figure. year_from and year_to narrow the summary to papers from those years, and exclude_self_citations recounts it without self-citations; any of them leaves out citations per year, which INSPIRE cannot narrow that way.

Fetch one paper's full INSPIRE-HEP record by recid, arXiv ID, or DOI: authors with affiliations and identifiers, abstract, publication references, arXiv and DOI identifiers, keywords, subjects, citation counts, linked experiments, texkeys, and whether HEPData holds its numerical tables (record DOI, latest version, table count, hepdata.net link). Also returns ready-made literature queries for the papers citing it and for its references. Large collaboration papers can list thousands of authors; max_authors caps the list while authorCount gives the full number.

Decode the vocabulary the other cern_inspire tools take: INSPIRE search syntax (field operators, boolean logic, sort orders, the 10,000-result window, and how malformed queries behave), identifier forms (recid, arXiv, DOI, BAI, ORCID, INSPIRE ID, institution recid, texkey, HEPData DOIs), the document_types and subjects filter values, citation-summary buckets, and HEPData record versions and DOIs. Static content with no upstream call; use it to build a query or to recover from an empty or unexpectedly broad result.

Find physicist profiles in INSPIRE-HEP by name, INSPIRE BAI, ORCID, INSPIRE ID, or author recid. Each profile carries its recid, BAI, ORCID, current and past positions, advisors, arXiv categories, links, awards, and a literatureQuery that selects the person's papers in cern_inspire_search_literature. A name returns ranked candidates (a bare surname can match tens of thousands of profiles, and a less-cited namesake can rank first), so confirm the person from positions and categories before passing a bai or recid to cern_inspire_get_citation_summary. An identifier matches exactly.

Find experiments, collaborations, and facilities in INSPIRE-HEP (ATLAS, CMS, DUNE, Belle II, …) by name, accelerator, or INSPIRE legacy name (CERN-LHC-CMS); digits alone look up an experiment recid. Each record carries the accelerator, host institutions, collaboration and subgroups, classification, lifecycle dates (proposed, approved, started, completed, ongoing), INSPIRE's paper count, a description, and a literatureQuery to pass to cern_inspire_search_literature or cern_inspire_get_citation_summary for the experiment's papers.

Find HEPData measurement records by physics content — process, observable, energy, collaboration — when the paper is unknown, through INSPIRE-HEP's index of every HEPData submission. Each hit carries the paper recids (pass to cern_inspire_get_paper), collaborations, keywords (reactions such as "P P --> TOP TOPBAR X", observables, centre-of-mass energies), the HEPData record DOI (recordDoi, the citation for the data), latest version, table count, and hepdataUrl, the hepdata.net record page that holds the table values; this tool does not return the values themselves. Only the first 10,000 results of a query are reachable.

Search INSPIRE-HEP papers with INSPIRE query syntax or free text, filtered by document type, subject, and year, sorted by relevance, recency, or citations. Returns one page of papers with recid, title, first author, date, citation counts, arXiv ID, DOI, publication, and an abstract snippet; pass a recid to cern_inspire_get_paper for the full record or to cern_inspire_export_citations ("recid:N") for BibTeX. INSPIRE never rejects malformed syntax: an unparsed operator widens or empties the match, so a very broad or empty result usually means the query needs fixing (cern_inspire_list_reference topic search_syntax). Only the first 10,000 results of a query are reachable.