cern-opendata-mcp-server

Search CERN Open Data Records

cern_opendata_search_records

Read-onlyIdempotent

Search the CERN Open Data Portal's datasets, software, environments, documentation and supplementary records with exact-vocabulary filters and an optional full-text query. The filters are experiment, record type, physics category, keyword, collision energy and type, file format, data-taking year, event count, availability, collection, and LHCb magnet polarity, stripping stream and stripping version. Returns compact hits with recids plus live facet counts. Each facet ignores its own filter, so its counts show the alternatives under the other filters. Filter values are exact upstream; common spellings are normalized, and cern_opendata_list_reference lists the vocabulary. Paging reaches the first 10,000 matches.

Input Schema

TableJSON Schema

Name	Required	Description
`page`	No	Page number, from 1, counting pages of the limit applied. page × limit may not exceed 10,000.
`sort`	No	bestmatch (relevance), mostrecent (by date_published, newest first), title (A-Z) or title_desc (Z-A). Omitted: bestmatch with a query, mostrecent (newest first) without.
`type`	No	Record types (OR): a primary (Dataset, Documentation, Environment, Software, Supplementaries, News) or Primary::Secondary such as Dataset::Collision or Dataset::Simulated. Up to 7. Omit for every served type; Glossary is not served.
`limit`	No	Hits per page, 1-50. A value above 50 is served at 50.
`query`	No	Full-text query, sent verbatim as an OpenSearch query_string (AND between terms; title matches weigh double). Field forms such as title:"…", recid:(1 OR 2) or run_period:("Run2012B") work; cern_opendata_list_reference with topic query_syntax lists them. Omit to browse by filters alone.
`year_to`	No	Latest data-taking year, inclusive. Alone, it means up to this year.
`category`	No	Physics categories of simulated datasets (OR): a primary such as Exotica, Higgs Physics, Standard Model Physics or Supersymmetry, or Primary::Secondary such as Higgs Physics::Standard Model. Up to 20; case and the separator are normalized, and a value holding a comma (Exotica::Heavy Fermions, Heavy Righ-Handed Neutrinos) is one item. Heavy-Ion Physics also matches its leading-space spelling. cern_opendata_list_reference topic categories lists every value.
`keywords`	No	Record keywords (OR), exact and case-sensitive (Education and education differ), sent as given. Up to 10; a keyword holding a comma is one item.
`file_type`	No	File formats and data tiers (OR), such as nanoaod, miniaod, aod, root, DAOD_PHYSLITE or csv. Up to 20; case is normalized for known values.
`year_from`	No	Earliest data-taking year, inclusive. Alone, it means this year onward; for one year, set year_from and year_to to it.
`collection`	No	Portal collections (OR), exact and case-sensitive, such as CMS-Validated-Runs; copy spellings from a record's collections field. Up to 10.
`experiment`	No	Experiments (OR): ALICE, ATLAS, CMS, DELPHI, JADE, LHCb, OPERA, PHENIX, TOTEM. Up to 9; case is normalized.
`max_events`	No	Maximum number of events, inclusive.
`min_events`	No	Minimum number of events, inclusive.
`availability`	No	Record availability (OR): online, partial, ondemand (on tape, requested before download) or requested. Up to 4.
`collision_type`	No	Collision types (OR): pp, PbPb, pPb, e+e-, Interfill. PbPb also matches the Pb-Pb spelling. Up to 6.
`magnet_polarity`	No	LHCb magnet polarities (OR): MagDown or MagUp, set on LHCb collision datasets. Up to 2; case is normalized.
`collision_energy`	No	Collision energies (OR), such as 7TeV, 8TeV, 13TeV or 5.02TeV. Up to 15; "13TeV, 13.6TeV" is one upstream value and one item.
`stripping_stream`	No	LHCb stripping streams (OR), such as BHADRON, CHARM, DIMUON, EW or LEPTONIC; they also match LHCb stripping documentation. Up to 11; case is normalized. cern_opendata_list_reference topic lhcb lists them.
`stripping_version`	No	LHCb stripping versions (OR), such as stripping21 or stripping21r1p2. Up to 12; case is normalized.

Output Schema

TableJSON Schema

Name	Required	Description
`cap`	No	The page size (limit) applied to this call.
`hits`	No	Matching records on this page.
`page`	No	The page returned.
`error`	No	Present when the call failed. Absent on success.
`shown`	No	Number of items returned on this page.
`facets`	No	Live facet counts. Each facet ignores its own filter, so its counts show the alternatives under the other filters. Terms facets list the first 10 values alphabetically (file_type up to 100), and type and category buckets their first 10 secondary values. other_count, subtypes_other_count and subcategories_other_count sum the counts of the values past those caps, so a record holding several of them counts once per value; other_count is 0 for year and number_events. cern_opendata_list_reference topics record_types and categories list every secondary value, and a Primary::Secondary type or category filter returns its record count as totalCount.
`notice`	No	Guidance for the next call: how to page on, why nothing matched and what to change, or a caveat about the results.
`has_more`	No	True when the next page holds matches and lies within the first 10,000. False on the last reachable page even when more matches exist; truncated and notice say so.
`truncated`	No	True when more results remain past this page; notice says how to reach them.
`totalCount`	No	Total matches for the query and filters.
`applied_filters`	No	The filters as the server applied them.

Schema Changelog

Changes observed during successful MCP inspections.

Changed32 schema fields changedOct 18, 2026

changedInput schema / properties / availability / description

Previous value: -"Record availability (OR): online, partial, ondemand (on tape, requested before download) or requested. Array or comma-separated string, up to 4."New value: +"Record availability (OR): online, partial, ondemand (on tape, requested before download) or requested. Up to 4."

changedInput schema / properties / category / description

Previous value: -"Physics categories of simulated datasets (OR): a primary such as Exotica, Higgs Physics, Standard Model Physics or Supersymmetry, or Primary::Secondary such as Higgs Physics::Standard Model. Array or comma-separated string, up to 20; case and the separator are normalized, and a known value holding a comma is kept whole. Heavy-Ion Physics also matches its leading-space spelling. cern_opendata_list_reference topic categories lists every value."New value: +"Physics categories of simulated datasets (OR): a primary such as Exotica, Higgs Physics, Standard Model Physics or Supersymmetry, or Primary::Secondary such as Higgs Physics::Standard Model. Up to 20; case and the separator are normalized, and a value holding a comma (Exotica::Heavy Fermions, Heavy Righ-Handed Neutrinos) is one item. Heavy-Ion Physics also matches its leading-space spelling. cern_opendata_list_reference topic categories lists every value."

changedInput schema / properties / collection / description

Previous value: -"Portal collections (OR), exact and case-sensitive, such as CMS-Validated-Runs; copy spellings from a record's collections field. Array or comma-separated string, up to 10."New value: +"Portal collections (OR), exact and case-sensitive, such as CMS-Validated-Runs; copy spellings from a record's collections field. Up to 10."

changedInput schema / properties / collision_energy / description

Previous value: -"Collision energies (OR), such as 7TeV, 8TeV, 13TeV or 5.02TeV. Array or comma-separated string, up to 15; \"13TeV, 13.6TeV\" is one upstream value and is kept whole."New value: +"Collision energies (OR), such as 7TeV, 8TeV, 13TeV or 5.02TeV. Up to 15; \"13TeV, 13.6TeV\" is one upstream value and one item."

changedInput schema / properties / collision_type / description

Previous value: -"Collision types (OR): pp, PbPb, pPb, e+e-, Interfill. PbPb also matches the Pb-Pb spelling. Array or comma-separated string, up to 6."New value: +"Collision types (OR): pp, PbPb, pPb, e+e-, Interfill. PbPb also matches the Pb-Pb spelling. Up to 6."

changedInput schema / properties / experiment / description

Previous value: -"Experiments (OR): ALICE, ATLAS, CMS, DELPHI, JADE, LHCb, OPERA, PHENIX, TOTEM. Array or comma-separated string, up to 9; case is normalized."New value: +"Experiments (OR): ALICE, ATLAS, CMS, DELPHI, JADE, LHCb, OPERA, PHENIX, TOTEM. Up to 9; case is normalized."

changedInput schema / properties / file_type / description

Previous value: -"File formats and data tiers (OR), such as nanoaod, miniaod, aod, root, DAOD_PHYSLITE or csv. Array or comma-separated string, up to 20; case is normalized for known values."New value: +"File formats and data tiers (OR), such as nanoaod, miniaod, aod, root, DAOD_PHYSLITE or csv. Up to 20; case is normalized for known values."

changedInput schema / properties / keywords / description

Previous value: -"Record keywords (OR), exact and case-sensitive (Education and education differ), sent as given. Array or comma-separated string, up to 10; pass a keyword holding a comma in an array."New value: +"Record keywords (OR), exact and case-sensitive (Education and education differ), sent as given. Up to 10; a keyword holding a comma is one item."

changedInput schema / properties / limit / description

Previous value: -"Hits per page, 1-50."New value: +"Hits per page, 1-50. A value above 50 is served at 50."

changedInput schema / properties / limit / maximum
```
Previous value: -50New value: +10000
```

changedInput schema / properties / magnet_polarity / description

Previous value: -"LHCb magnet polarities (OR): MagDown or MagUp, set on LHCb collision datasets. Array or comma-separated string, up to 2; case is normalized."New value: +"LHCb magnet polarities (OR): MagDown or MagUp, set on LHCb collision datasets. Up to 2; case is normalized."

changedInput schema / properties / page / description

Previous value: -"Page number, from 1. page × limit may not exceed 10,000."New value: +"Page number, from 1, counting pages of the limit applied. page × limit may not exceed 10,000."

changedInput schema / properties / stripping_stream / description

Previous value: -"LHCb stripping streams (OR), such as BHADRON, CHARM, DIMUON, EW or LEPTONIC; they also match LHCb stripping documentation. Array or comma-separated string, up to 11; case is normalized. cern_opendata_list_reference topic lhcb lists them."New value: +"LHCb stripping streams (OR), such as BHADRON, CHARM, DIMUON, EW or LEPTONIC; they also match LHCb stripping documentation. Up to 11; case is normalized. cern_opendata_list_reference topic lhcb lists them."

changedInput schema / properties / stripping_version / description

Previous value: -"LHCb stripping versions (OR), such as stripping21 or stripping21r1p2. Array or comma-separated string, up to 12; case is normalized."New value: +"LHCb stripping versions (OR), such as stripping21 or stripping21r1p2. Up to 12; case is normalized."

changedInput schema / properties / type / description

Previous value: -"Record types (OR): a primary (Dataset, Documentation, Environment, Software, Supplementaries, News) or Primary::Secondary such as Dataset::Collision or Dataset::Simulated. Array or comma-separated string, up to 7. Omit for every served type; Glossary is not served."New value: +"Record types (OR): a primary (Dataset, Documentation, Environment, Software, Supplementaries, News) or Primary::Secondary such as Dataset::Collision or Dataset::Simulated. Up to 7. Omit for every served type; Glossary is not served."

changedOutput schema / properties / error / properties / data / properties / reason / description

Previous value: -"Machine-readable failure mode. Declared by this tool: `invalid_query`: query leaves a parenthesis, range bracket or double quote unbalanced, or ends in an escaping backslash (refused before any request); or the portal rejected the query string (invalid query syntax), or answered another 400 the server did not anticipate, whose upstream message is carried. `query_server_error`: Every attempt of a search with query set answered HTTP 500, as the portal does for some malformed queries in place of its 400 syntax rejection. `page_window_exceeded`: page × limit exceeds 10,000, the deepest match the portal pages to. `invalid_range`: year_from is after year_to, or min_events is above max_events. `rate_limited`: The portal's 60-a-minute budget is spent: it answered 429, or the request could not start within the call's deadline. data.retryAfter is set. `upstream_unreadable`: The portal answered with a body the server could not read: not JSON, missing the expected envelope, or over the byte ceiling (then data.retryable is false). Also raised when a search answers 404. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_query`: query leaves a parenthesis, range bracket or double quote unbalanced, or ends in an escaping backslash (refused before any request); or the portal rejected the query string (invalid query syntax), or answered another 400 the server did not anticipate, whose upstream message is carried. `query_server_error`: Every attempt of a search with query set answered HTTP 500, as the portal does for some malformed queries in place of its 400 syntax rejection. `page_window_exceeded`: page × limit, the limit applied (at most 50), exceeds 10,000, the deepest match the portal pages to. `invalid_range`: year_from is after year_to, or min_events is above max_events. `rate_limited`: The portal's 60-a-minute budget is spent: it answered 429, or the request could not start within the call's deadline. data.retryAfter is set. `upstream_unreadable`: The portal answered with a body the server could not read: not JSON, missing the expected envelope, or over the byte ceiling (then data.retryable is false). Also raised when a search answers 404. Other values are possible when a failure originates below the handler."

changedOutput schema / properties / facets / description

Previous value: -"Live facet counts. Each facet ignores its own filter, so its counts show the alternatives under the other filters. Terms facets list the first 10 values alphabetically (file_type up to 100). other_count is 0 for year and number_events."New value: +"Live facet counts. Each facet ignores its own filter, so its counts show the alternatives under the other filters. Terms facets list the first 10 values alphabetically (file_type up to 100), and type and category buckets their first 10 secondary values. other_count, subtypes_other_count and subcategories_other_count sum the counts of the values past those caps, so a record holding several of them counts once per value; other_count is 0 for year and number_events. cern_opendata_list_reference topics record_types and categories list every secondary value, and a Primary::Secondary type or category filter returns its record count as totalCount."

changedOutput schema / properties / facets / properties / availability / properties / other_count / description

Previous value: -"Records past the bucket cap."New value: +"Summed count of the values past the bucket cap, not a record count."

added

Output schema / properties / facets / properties / category / properties / buckets / items / properties / subcategories_other_count

Added value: +{
+  "description": "Summed count of the secondary categories past the 10 listed, not a record count; absent when the list is whole.",
+  "type": "number"
+}

changedOutput schema / properties / facets / properties / category / properties / other_count / description

Previous value: -"Records past the bucket cap."New value: +"Summed count of the values past the bucket cap, not a record count."

changedOutput schema / properties / facets / properties / collision_energy / properties / other_count / description

Previous value: -"Records past the bucket cap."New value: +"Summed count of the values past the bucket cap, not a record count."

changedOutput schema / properties / facets / properties / collision_type / properties / other_count / description

Previous value: -"Records past the bucket cap."New value: +"Summed count of the values past the bucket cap, not a record count."

changedOutput schema / properties / facets / properties / experiment / properties / other_count / description

Previous value: -"Records past the bucket cap."New value: +"Summed count of the values past the bucket cap, not a record count."

changedOutput schema / properties / facets / properties / file_type / properties / other_count / description

Previous value: -"Records past the bucket cap."New value: +"Summed count of the values past the bucket cap, not a record count."

changedOutput schema / properties / facets / properties / keywords / properties / other_count / description

Previous value: -"Records past the bucket cap."New value: +"Summed count of the values past the bucket cap, not a record count."

changedOutput schema / properties / facets / properties / magnet_polarity / properties / other_count / description

Previous value: -"Records past the bucket cap."New value: +"Summed count of the values past the bucket cap, not a record count."

changedOutput schema / properties / facets / properties / number_events / properties / other_count / description

Previous value: -"Records past the bucket cap."New value: +"Summed count of the values past the bucket cap, not a record count."

changedOutput schema / properties / facets / properties / stripping_stream / properties / other_count / description

Previous value: -"Records past the bucket cap."New value: +"Summed count of the values past the bucket cap, not a record count."

changedOutput schema / properties / facets / properties / stripping_version / properties / other_count / description

Previous value: -"Records past the bucket cap."New value: +"Summed count of the values past the bucket cap, not a record count."

added

Output schema / properties / facets / properties / type / properties / buckets / items / properties / subtypes_other_count

Added value: +{
+  "description": "Summed count of the secondary types past the 10 listed, not a record count; absent when the list is whole.",
+  "type": "number"
+}

changedOutput schema / properties / facets / properties / type / properties / other_count / description

Previous value: -"Records past the bucket cap."New value: +"Summed count of the values past the bucket cap, not a record count."

changedOutput schema / properties / facets / properties / year / properties / other_count / description

Previous value: -"Records past the bucket cap."New value: +"Summed count of the values past the bucket cap, not a record count."

First observedOct 2, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent and openWorld, so safety is covered. The description adds genuinely non-obvious behavior: facet counts ignore their own filter, values are exact upstream with normalization of common spellings, and paging stops at 10,000 matches. Return shape and pagination detail are somewhat thinner, keeping it below 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?

Purpose and return shape are front-loaded, and every sentence carries information (filters, facet behavior, vocabulary routing, paging cap). The long mid-sentence enumeration of filters is dense but justified for a 20-parameter tool; nothing is redundant.

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 20-param search tool with an output schema, the description covers what an agent needs: purpose, filter vocabulary, normalization rules, facet semantics, pagination ceiling, and the sibling that supplies valid values. Return-value explanation is correctly left to the output schema.

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 description coverage is 100%, so the schema already documents each of the 20 parameters, establishing a baseline of 3. The description adds cross-cutting meaning the schema scatters: the full filter list as a set, the normalization/exactness policy, and the facet-count semantics that govern how filter values should be chosen.

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 (Search) plus the exact resource scope (CERN Open Data Portal datasets, software, environments, documentation, supplementary records) and enumerates the filter vocabulary. This clearly distinguishes it from siblings like cern_opendata_get_records or cern_opendata_list_reference without needing to open either schema.

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?

Explains the two usage modes (exact-vocabulary filters, optional full-text query) and routes agents to cern_opendata_list_reference for the controlled vocabulary. It does not explicitly say when to prefer cern_opendata_get_records or the other lookup siblings, so it falls short of a full when/when-not statement.

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

All cern-opendata-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.