cern-inspire-mcp-server

Get INSPIRE citation summary

cern_inspire_get_citation_summary

Read-onlyIdempotent

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 "). 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.

Input Schema

TableJSON Schema

Name	Required	Description
`query`	No	An INSPIRE literature query, e.g. "collaboration:atlas", "t neutrino oscillation", "a Edward.Witten.1", or "affid:902725" for an institution's papers (CERN; affid takes the institution recid that cern_inspire_search_authors and cern_inspire_search_experiments return). Literature queries do not match ORCIDs; pass an ORCID as author. Pass this or author, not both.
`author`	No	One author identifier: INSPIRE BAI (Edward.Witten.1, exact and case-sensitive), ORCID (0000-0002-7752-6073 or an orcid.org URL), INSPIRE ID (INSPIRE-00136372), or author recid. Not a name — resolve names with cern_inspire_search_authors first. Pass this or query, not both.
`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.
`exclude_self_citations`	No	Count citations without self-citations (INSPIRE's definition), default false. Setting it leaves out citationsByYear, which always includes self-citations.

Output Schema

TableJSON Schema

Name	Required	Description
`all`	No	Totals over citeable papers.
`error`	No	Present when the call failed. Absent on success.
`hIndex`	No	h-index for all citeable and for published papers.
`notice`	No	Guidance when no citeable paper matched, or when citations per year were left out or could not be read.
`target`	No	What the summary covers.
`buckets`	No	Papers per citation range, for all citeable and for published papers.
`published`	No	Totals over published papers.
`appliedFilters`	No	Filters applied, e.g. "document_types=published; years=2012–2015; exclude_self_citations=true", or "none".
`citeablePapers`	No	Citeable papers among the matched records.
`effectiveQuery`	No	The literature query sent to INSPIRE.
`matchedRecords`	No	Literature records the query matched, citeable or not.
`citationsByYear`	No	Citations per year in ascending order, each counted in the year of the citing record's earliest date, self-citations included, over every matched record (citeable or not), so the sum can exceed all.citations. A year without citations has no row, and the current year counts citations to date. Empty when nothing matched or no matched record is cited; omitted when year_from, year_to, or exclude_self_citations is set, when INSPIRE did not return the series, or when the query matches more than about 150,000 records, which INSPIRE cannot count in time, unless INSPIRE answers within about 2 s (a series it has cached).

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 2, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations cover the safety profile (readOnly/idempotent/openWorld), and the description adds real behavioral context the annotations do not: that any of the year/self-citation filters removes citations-per-year from the output because INSPIRE cannot narrow it that way. It stops short of describing performance or rate limits, so not a 5.

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?

The metrics are front-loaded before the parameter guidance, and each sentence carries substantive information. It is dense and on the long side, but there is little pure filler; only the inline enumeration of citation buckets slightly duplicates the output schema's job.

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?

For a 7-parameter, zero-required tool with an output schema, the description covers input alternatives, prerequisite resolution, filter interactions, and the mutable-output caveat. An agent has everything needed to select and invoke it correctly, with no gaps in the description's own responsibilities.

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

Parameters4/5

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

Schema coverage is 100%, which already sets a strong baseline, but the description goes further by explaining what counts as valid author identifiers (BAI/ORCID/INSPIRE ID/recid, not a name) and that query accepts topics, collaborations, institutions, or 'a <BAI>'. It adds meaning beyond the schema rather than restating it.

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 and resource ('Compute INSPIRE-HEP's citation summary') and enumerates the exact metrics produced (h-index, citation totals, per-bucket counts, citations per year), which lets an agent distinguish it from siblings like cern_inspire_export_citations or cern_inspire_search_literature.

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?

Gives an explicit constraint ('Pass exactly one of author ... or query'), a prerequisite ('resolve a name with cern_inspire_search_authors first'), and describes how the optional filters narrow the result. It routes the agent to the sibling needed before calling this tool.

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.