cern-inspire-mcp-server

Search INSPIRE literature

cern_inspire_search_literature

Read-onlyIdempotent

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.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`page`	No	Page number, starting at 1. page × size may not exceed 10,000.
`size`	No	Papers per page (1–100, default 10).
`sort`	No	Result order: relevance (default), mostrecent, or mostcited.	relevance
`query`	Yes	INSPIRE query syntax or free text. Common operators: "a Jane.Doe.1" or "a Doe, J" (author), "t higgs boson" (title words), "cn atlas" or "collaboration:atlas" (collaboration), "date > 2015", "topcite 500+" (cited 500+ times), "refersto:recid:451647" (papers citing a record), "citedby:recid:451647" (its references), "j Phys.Rev.Lett." (journal), "eprint 1207.7214"; combine with and/or/not. Bare words search all fields. INSPIRE does not reject malformed syntax; see cern_inspire_list_reference topic search_syntax for the rest.
`year_to`	No	Latest year to include (1900–2100, inclusive), matched on the earliest date INSPIRE records for the paper. Omit for no upper bound.
`subjects`	No	Restrict to INSPIRE subject categories (up to 4). Multiple values must ALL hold, not either. Values: Astrophysics, Phenomenology-HEP, Theory-HEP, Quantum Physics, Unknown, Gravitation and Cosmology, Experiment-HEP, Theory-Nucl, Accelerators, Instrumentation, General Physics, Experiment-Nucl, Math and Math Physics, Condensed Matter, Computing, Lattice, Other, Data Analysis and Statistics.
`year_from`	No	Earliest year to include (1900–2100, inclusive), matched on the earliest date INSPIRE records for the paper. Omit for no lower bound.
`document_types`	No	Restrict to INSPIRE document types (up to 4). Multiple values must ALL hold (published + review = published reviews), not either. Values: article, published, conference paper, thesis, review, note, proceedings, lectures, book chapter, book, introductory, activity report, report.

Output Schema

TableJSON Schema

Name	Required	Description
`cap`	No	The page size applied.
`page`	No	The page returned.
`size`	No	The page size requested.
`error`	No	Present when the call failed. Absent on success.
`shown`	No	Number of papers on this page.
`notice`	No	Guidance on an empty, very broad, or paged result.
`papers`	No	The papers on this page, in the requested order.
`hasMore`	No	True when INSPIRE has a further page of results.
`nextPage`	No	The page number to request next, when one exists within the 10,000-result window.
`truncated`	No	True when more results exist beyond this page.
`totalCount`	No	Total literature records the query matched.
`appliedFilters`	No	Sort and filters applied, e.g. "sort=mostcited; years=2012–2015", or "none".

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 2, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover safety (readOnly, idempotent, openWorld), but the description adds non-obvious behavior: only the first 10,000 results are reachable, and INSPIRE never rejects malformed syntax so a broad/empty result signals a query bug. That is exactly the kind of failure-mode context annotations cannot express.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose and filters, then return fields, routing, and caveats. Every sentence is useful, though the return-field list and malformed-syntax warning partially duplicate the schema and could be tightened.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 8 parameters, an output schema, and rich annotations, the description still supplies the return shape, result cap, sibling routing, and query-syntax pitfall. Nothing an agent needs to call this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the query parameter already documents the INSPIRE operators, so the schema does the heavy lifting. The description's mention of document type/subject/year filtering and sorting mostly restates structured fields rather than adding syntax beyond them.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Search INSPIRE-HEP papers') plus scope: query syntax, filters, sort order. It is clearly distinguishable from siblings like cern_inspire_search_authors or cern_inspire_search_experiments without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes the agent: pass a recid to cern_inspire_get_paper for the full record or to cern_inspire_export_citations for BibTeX, and points to cern_inspire_list_reference topic search_syntax when queries misbehave. This is concrete when-to-use-which-tool guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All cern-inspire-mcp-server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.