cern-inspire-mcp-server

Get INSPIRE paper

cern_inspire_get_paper

Read-onlyIdempotent

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.

Input Schema

TableJSON Schema

Name	Required	Description
`paper`	Yes	INSPIRE recid (e.g. 451647), arXiv ID (1207.7214 or hep-th/9711200, with or without 'arXiv:', a version suffix, or an https://arxiv.org/abs/ or https://arxiv.org/pdf/ prefix), DOI (10.1016/…, with or without 'doi:' or an https://doi.org/ prefix; no * or ? wildcards), an https://inspirehep.net/literature/<recid> URL, or HEPData's ins<recid> form, alone or in an https://www.hepdata.net/record/ins<recid> URL. Up to 256 characters.
`max_authors`	No	Most authors to list (nonnegative integer, default 25; values above 500 use 500). Zero lists no authors. The full count is always in authorCount.
`author_offset`	No	Zero-based starting position in the normalized author list (default 0). Use nextAuthorOffset from the previous page.

Output Schema

TableJSON Schema

Name	Required	Description
`cap`	No	The max_authors cap applied.
`core`	No	True when INSPIRE classes the paper as core HEP, when recorded.
`date`	No	Earliest date INSPIRE records for the paper: YYYY, YYYY-MM, or YYYY-MM-DD.
`dois`	No	DOIs of the paper.
`urls`	No	External links INSPIRE records for the paper.
`error`	No	Present when the call failed. Absent on success.
`recid`	No	INSPIRE literature record ID.
`shown`	No	Number of authors listed.
`title`	No	Title as text: publisher HTML, JATS, and MathML converted (scripts as _x or ^{xy}), LaTeX left as published.
`notice`	No	Guidance when the recid asked for was merged into this record, the author list was capped, HEPData availability could not be checked, or the paper has more than one HEPData record.
`arxivId`	No	arXiv identifier, when the paper has one.
`authors`	No	Authors in record order from authorOffset, capped at the effective max_authors budget.
`hepdata`	No	HEPData availability for the paper's numerical tables.
`texkeys`	No	INSPIRE texkeys (BibTeX citation keys), current first.
`abstract`	No	Full abstract as text (arXiv-sourced when available): publisher markup converted like title, LaTeX left as published.
`citeable`	No	INSPIRE citeable flag, when recorded.
`keywords`	No	Keywords, de-duplicated.
`licenses`	No	Licences recorded for the paper.
`refereed`	No	True when published in a refereed venue, when recorded.
`subjects`	No	INSPIRE subject categories.
`truncated`	No	True when available authors remain after this page, including a zero-budget page.
`inspireUrl`	No	The paper on inspirehep.net.
`mergedFrom`	No	The recid asked for, when INSPIRE had merged that record into this one and redirects it here; cite and query this record by recid.
`resolvedAs`	No	Which identifier form the paper input was resolved from.
`authorCount`	No	Total number of authors on the paper.
`citingQuery`	No	Literature query for papers citing this one; pass to cern_inspire_search_literature.
`experiments`	No	Accelerator experiments linked to the paper.
`authorOffset`	No	Zero-based starting position in the normalized available author list.
`preprintDate`	No	Preprint date, when recorded.
`publications`	No	Publication references (journal, volume, year, pages).
`citationCount`	No	Citations INSPIRE counts for the paper.
`documentTypes`	No	INSPIRE document types.
`numberOfPages`	No	Page count, when recorded.
`reportNumbers`	No	Report numbers.
`abstractSource`	No	Who supplied the abstract (e.g. arXiv, a publisher).
`collaborations`	No	Collaborations credited on the paper; empty for most non-collaboration papers.
`alternateTitles`	No	Other titles INSPIRE records (translations, preprint titles), converted to text like title.
`arxivCategories`	No	arXiv categories of the e-print.
`publicationDate`	No	Publication (imprint) date, when recorded.
`referencesQuery`	No	Literature query for this paper's references; pass to cern_inspire_search_literature.
`nextAuthorOffset`	No	Pass as author_offset to read the next page; absent when no authors remain or the budget is zero.
`citationCountWithoutSelf`	No	Citations excluding self-citations, when INSPIRE reports it.

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedOct 16, 2026

addedInput schema / properties / author_offset

Added value: +{
+  "default": 0,
+  "description": "Zero-based starting position in the normalized author list (default 0). Use nextAuthorOffset from the previous page.",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}

changedInput schema / properties / max_authors / description

Previous value: -"Most authors to list (0–500, default 25). The full count is always in authorCount."New value: +"Most authors to list (nonnegative integer, default 25; values above 500 use 500). Zero lists no authors. The full count is always in authorCount."

changedInput schema / properties / max_authors / maximum
```
Previous value: -500New value: +9007199254740991
```

changedOutput schema / anyOf

Previous value: -[
-  {
-    "not": {
-      "required": [
-        "error"
-      ]
-    },
-    "required": [
-      "recid",
-      "resolvedAs",
-      "title",
-      "alternateTitles",
-      "authorCount",
-      "authors",
-      "collaborations",
-      "experiments",
-      "publications",
-      "arxivCategories",
-      "dois",
-      "reportNumbers",
-      "keywords",
-      "subjects",
-      "documentTypes",
-      "citationCount",
-      "texkeys",
-      "urls",
-      "licenses",
-      "inspireUrl",
-      "citingQuery",
-      "referencesQuery",
-      "hepdata",
-      "truncated",
-      "shown",
-      "cap"
-    ]
-  },
-  {
-    "required": [
-      "error"
-    ]
-  }
-]New value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "recid",
+      "resolvedAs",
+      "title",
+      "alternateTitles",
+      "authorCount",
+      "authorOffset",
+      "authors",
+      "collaborations",
+      "experiments",
+      "publications",
+      "arxivCategories",
+      "dois",
+      "reportNumbers",
+      "keywords",
+      "subjects",
+      "documentTypes",
+      "citationCount",
+      "texkeys",
+      "urls",
+      "licenses",
+      "inspireUrl",
+      "citingQuery",
+      "referencesQuery",
+      "hepdata",
+      "truncated",
+      "shown",
+      "cap"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]

addedOutput schema / properties / authorOffset

Added value: +{
+  "description": "Zero-based starting position in the normalized available author list.",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}

changedOutput schema / properties / authors / description

Previous value: -"Authors in record order, capped at max_authors."New value: +"Authors in record order from authorOffset, capped at the effective max_authors budget."

addedOutput schema / properties / nextAuthorOffset

Added value: +{
+  "description": "Pass as author_offset to read the next page; absent when no authors remain or the budget is zero.",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}

changedOutput schema / properties / truncated / description

Previous value: -"True when the author list was capped at max_authors."New value: +"True when available authors remain after this page, including a zero-budget page."

First observedOct 2, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so the safety profile is covered. The description adds real operational context beyond that: large collaboration papers can list thousands of authors, max_authors caps the list, and authorCount always exposes the true total.

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 verb and identifier forms are front-loaded, and the long field enumeration is dense but earns its place by telling the agent what the record contains. The pagination note is useful rather than filler. Slightly long overall but not padded.

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?

An output schema exists, yet the description still sketches the payload (authors, abstract, identifiers, HEPData tables, ready-made queries) and the key pagination mechanics. Nothing needed to invoke it 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%, so the baseline is 3. The description restates the max_authors/authorCount relationship already documented in the schema and adds no format or syntax detail the schema lacks, so it does not exceed baseline.

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?

Opens with a specific verb+resource ("Fetch one paper's full INSPIRE-HEP record") and immediately names the three identifier forms accepted. This clearly separates it from discovery-oriented siblings like 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 Guidelines4/5

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

The identifier-based framing makes the usage context clear: call this when you already hold a recid/arXiv ID/DOI. It stops short of explicitly contrasting with search_literature or noting what to do when you only have a title, so no exclusion is stated.

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.