eur-lex-mcp-server

Raw CELLAR SPARQL Query

eurlex_query_sparql

Read-only

Run a raw, read-only SPARQL SELECT against the CELLAR Virtuoso endpoint — an escape hatch for CDM ontology traversals the curated tools do not cover. Only SELECT is accepted; update forms and ASK/CONSTRUCT/DESCRIBE are rejected before execution, and results are capped at 100. The cdm:, skos:, and xsd: prefixes are auto-injected.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`sparql_query`	Yes	A read-only SPARQL SELECT query. Leading comments and PREFIX/BASE declarations are allowed; the cdm:, skos:, and xsd: prefixes are auto-injected. LIMIT is injected at 100 if absent, or capped to 100. Key CDM predicates: cdm:resource_legal_id_celex (CELEX), cdm:work_date_document (date), cdm:work_has_resource-type (type), cdm:work_is_about_concept_eurovoc (EuroVoc subject), cdm:work_cites_work (citation). CELEX is an xsd:string literal — match it as a typed triple, ?work cdm:resource_legal_id_celex "32016R0679"^^xsd:string (an untyped literal matches nothing, in a triple or in FILTER(?celex = "…"), and a FILTER(STR(…)) comparison scans every CELEX). For text, use bif:contains with a single-quoted phrase.
`timeout_hint`	No	Optional client-side timeout in milliseconds (1000–55000). Defaults apply when omitted; the endpoint hard limit is 60 seconds.

Output Schema

TableJSON Schema

Name	Required	Description
`cap`	No	The server-enforced result ceiling that was applied.
`error`	No	Present when the call failed. Absent on success.
`shown`	No	Number of binding rows returned in this response.
`total`	No	Number of binding rows returned (capped at 100 by the server).
`notice`	No	On a zero-row result whose query has an untyped string literal as a triple object: how to type or language-tag it, since CELLAR stores identifiers as typed literals that an untyped one never matches.
`bindings`	No	Raw SPARQL binding rows. To extract a value from a row: row["varName"]?.value. Use the variables array to iterate in query order.
`truncated`	No	True when the server-enforced result ceiling capped the rows and more may exist upstream — narrow the query with FILTERs to see the rest.
`variables`	No	Variable names from the SELECT head, in query order.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedSep 26, 2026

changedInput schema / properties / sparql_query / description

Previous value: -"A read-only SPARQL SELECT query. Leading comments and PREFIX/BASE declarations are allowed; the cdm:, skos:, and xsd: prefixes are auto-injected. LIMIT is injected at 100 if absent, or capped to 100. Key CDM predicates: cdm:resource_legal_id_celex (CELEX), cdm:work_date_document (date), cdm:work_has_resource-type (type), cdm:work_is_about_concept_eurovoc (EuroVoc subject), cdm:work_cites_work (citation). CELEX is an xsd:string literal — match it as a typed triple, ?work cdm:resource_legal_id_celex \"32016R0679\"^^xsd:string (an untyped literal matches nothing, and a FILTER(STR(…)) comparison scans every CELEX). For text, use bif:contains with a single-quoted phrase."New value: +"A read-only SPARQL SELECT query. Leading comments and PREFIX/BASE declarations are allowed; the cdm:, skos:, and xsd: prefixes are auto-injected. LIMIT is injected at 100 if absent, or capped to 100. Key CDM predicates: cdm:resource_legal_id_celex (CELEX), cdm:work_date_document (date), cdm:work_has_resource-type (type), cdm:work_is_about_concept_eurovoc (EuroVoc subject), cdm:work_cites_work (citation). CELEX is an xsd:string literal — match it as a typed triple, ?work cdm:resource_legal_id_celex \"32016R0679\"^^xsd:string (an untyped literal matches nothing, in a triple or in FILTER(?celex = \"…\"), and a FILTER(STR(…)) comparison scans every CELEX). For text, use bif:contains with a single-quoted phrase."

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

Previous value: -"Machine-readable failure mode. Declared by this tool: `not_read_only`: The query is not a read-only SELECT — an update or non-SELECT query form was supplied. `sparql_error`: Virtuoso returned a syntax or semantic error — the query is malformed. `sparql_timeout`: The query exceeded the client-side timeout (timeout_hint, default 55 s) or the 60-second Virtuoso execution limit. Neither is retried: the call fails inside the configured bound. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `not_read_only`: The query is a SPARQL Update operation (INSERT, DELETE, WITH, LOAD, CLEAR, CREATE, DROP, COPY, MOVE, or ADD). `unsupported_query_form`: The query is not a SELECT: an ASK, CONSTRUCT, or DESCRIBE form, an unrecognized keyword, or no query keyword after the prologue. `sparql_error`: Virtuoso returned a syntax or semantic error — the query is malformed. `sparql_timeout`: The query exceeded the client-side timeout (timeout_hint, default 55 s) or the 60-second Virtuoso execution limit. Neither is retried: the call fails inside the configured bound. Other values are possible when a failure originates below the handler."

changedOutput schema / properties / error / properties / data / properties / reason / examples

Previous value: -[
-  "not_read_only",
-  "sparql_error",
-  "sparql_timeout"
-]New value: +[
+  "not_read_only",
+  "unsupported_query_form",
+  "sparql_error",
+  "sparql_timeout"
+]

addedOutput schema / properties / notice

Added value: +{
+  "description": "On a zero-row result whose query has an untyped string literal as a triple object: how to type or language-tag it, since CELLAR stores identifiers as typed literals that an untyped one never matches.",
+  "type": "string"
+}

Changed1 schema field changedSep 25, 2026

changedInput schema / properties / sparql_query / description

Previous value: -"A read-only SPARQL SELECT query. Leading comments and PREFIX/BASE declarations are allowed; the cdm:, skos:, and xsd: prefixes are auto-injected. LIMIT is injected at 100 if absent, or capped to 100. Key CDM predicates: cdm:resource_legal_id_celex (CELEX), cdm:work_date_document (date), cdm:work_has_resource-type (type), cdm:work_is_about_concept_eurovoc (EuroVoc subject), cdm:work_cites_work (citation). CELEX is an xsd:string literal — match it with FILTER(STR(?celex) = \"…\"). For text, use bif:contains with a single-quoted phrase."New value: +"A read-only SPARQL SELECT query. Leading comments and PREFIX/BASE declarations are allowed; the cdm:, skos:, and xsd: prefixes are auto-injected. LIMIT is injected at 100 if absent, or capped to 100. Key CDM predicates: cdm:resource_legal_id_celex (CELEX), cdm:work_date_document (date), cdm:work_has_resource-type (type), cdm:work_is_about_concept_eurovoc (EuroVoc subject), cdm:work_cites_work (citation). CELEX is an xsd:string literal — match it as a typed triple, ?work cdm:resource_legal_id_celex \"32016R0679\"^^xsd:string (an untyped literal matches nothing, and a FILTER(STR(…)) comparison scans every CELEX). For text, use bif:contains with a single-quoted phrase."

Changed1 schema field changedSep 10, 2026

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

Previous value: -"Machine-readable failure mode. Declared by this tool: `not_read_only`: The query is not a read-only SELECT — an update or non-SELECT query form was supplied. `sparql_error`: Virtuoso returned a syntax or semantic error — the query is malformed. `sparql_timeout`: Query exceeded the 60-second Virtuoso hard limit. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `not_read_only`: The query is not a read-only SELECT — an update or non-SELECT query form was supplied. `sparql_error`: Virtuoso returned a syntax or semantic error — the query is malformed. `sparql_timeout`: The query exceeded the client-side timeout (timeout_hint, default 55 s) or the 60-second Virtuoso execution limit. Neither is retried: the call fails inside the configured bound. Other values are possible when a failure originates below the handler."

Changed6 schema fields changedAug 22, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

addedInput schema / additionalProperties
```
Added value: +false
```

changedOutput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

addedOutput schema / anyOf

Added value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "bindings",
+      "variables",
+      "total"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]

addedOutput schema / properties / error

Added value: +{
+  "additionalProperties": {},
+  "description": "Present when the call failed. Absent on success.",
+  "properties": {
+    "code": {
+      "description": "JSON-RPC error code for this failure.",
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "data": {
+      "additionalProperties": {},
+      "properties": {
+        "reason": {
+          "description": "Machine-readable failure mode. Declared by this tool: `not_read_only`: The query is not a read-only SELECT — an update or non-SELECT query form was supplied. `sparql_error`: Virtuoso returned a syntax or semantic error — the query is malformed. `sparql_timeout`: Query exceeded the 60-second Virtuoso hard limit. Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "not_read_only",
+            "sparql_error",
+            "sparql_timeout"
+          ],
+          "type": "string"
+        },
+        "recovery": {
+          "additionalProperties": {},
+          "description": "Actionable next step for the caller.",
+          "properties": {
+            "hint": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "hint"
+          ],
+          "type": "object"
+        },
+        "retryable": {
+          "description": "Whether retrying may succeed.",
+          "type": "boolean"
+        }
+      },
+      "type": "object"
+    },
+    "message": {
+      "description": "Human-readable description of what went wrong.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "code",
+    "message"
+  ],
+  "type": "object"
+}

removedOutput schema / required

Removed value: -[
-  "bindings",
-  "variables",
-  "total"
-]

Changed4 schema fields changedJul 16, 2026

changedOutput schema / properties / bindings / items / description

Previous value: -"A single SPARQL result row. Each key is a SELECT variable name; each value is a SPARQL term object with \"type\" (e.g. \"uri\", \"literal\") and \"value\" (the string value) fields."New value: +"A single SPARQL result row. Each key is a SELECT variable name; each value is a SPARQL term object with \"type\" (\"uri\", \"literal\", or \"bnode\") and \"value\" (the string value), plus \"datatype\" (an IRI) on a typed literal or \"xml:lang\" (a language tag) on a language-tagged literal — the two are mutually exclusive. A variable left unbound by an OPTIONAL has no key in the row at all."

addedOutput schema / properties / cap

Added value: +{
+  "description": "The server-enforced result ceiling that was applied.",
+  "type": "number"
+}

addedOutput schema / properties / shown

Added value: +{
+  "description": "Number of binding rows returned in this response.",
+  "type": "number"
+}

addedOutput schema / properties / truncated

Added value: +{
+  "description": "True when the server-enforced result ceiling capped the rows and more may exist upstream — narrow the query with FILTERs to see the rest.",
+  "type": "boolean"
+}

Changed2 schema fields changedJul 4, 2026

changedInput schema / properties / sparql_query / description

Previous value: -"A read-only SPARQL SELECT query to execute against CELLAR. Non-SELECT queries (updates such as DELETE/INSERT, or ASK/CONSTRUCT/DESCRIBE) are rejected before execution. Leading comments and PREFIX/BASE declarations are allowed before the SELECT keyword. The cdm:, skos:, and xsd: prefixes are auto-injected. LIMIT is injected at 100 if absent or capped to 100 if above that threshold."New value: +"A read-only SPARQL SELECT query. Leading comments and PREFIX/BASE declarations are allowed; the cdm:, skos:, and xsd: prefixes are auto-injected. LIMIT is injected at 100 if absent, or capped to 100. Key CDM predicates: cdm:resource_legal_id_celex (CELEX), cdm:work_date_document (date), cdm:work_has_resource-type (type), cdm:work_is_about_concept_eurovoc (EuroVoc subject), cdm:work_cites_work (citation). CELEX is an xsd:string literal — match it with FILTER(STR(?celex) = \"…\"). For text, use bif:contains with a single-quoted phrase."

changedInput schema / properties / timeout_hint / description

Previous value: -"Optional client-side timeout for this request, in milliseconds (1000–55000). When omitted, the default timeout applies; the endpoint hard limit is 60 seconds."New value: +"Optional client-side timeout in milliseconds (1000–55000). Defaults apply when omitted; the endpoint hard limit is 60 seconds."

Changed1 schema field changedJul 3, 2026

changedInput schema / properties / timeout_hint / description

Previous value: -"Optional client-side timeout for this request, in milliseconds (1000–55000). When omitted, the server-configured default (SPARQL_QUERY_TIMEOUT_MS, 55000) applies. Virtuoso hard limit is 60 seconds."New value: +"Optional client-side timeout for this request, in milliseconds (1000–55000). When omitted, the default timeout applies; the endpoint hard limit is 60 seconds."

Changed2 schema fields changedJun 30, 2026

changedInput schema / properties / sparql_query / description

Previous value: -"A SPARQL SELECT query to execute against CELLAR. The cdm:, skos:, and xsd: prefixes are auto-injected. LIMIT is injected at 100 if absent or capped to 100 if above that threshold."New value: +"A read-only SPARQL SELECT query to execute against CELLAR. Non-SELECT queries (updates such as DELETE/INSERT, or ASK/CONSTRUCT/DESCRIBE) are rejected before execution. Leading comments and PREFIX/BASE declarations are allowed before the SELECT keyword. The cdm:, skos:, and xsd: prefixes are auto-injected. LIMIT is injected at 100 if absent or capped to 100 if above that threshold."

changedInput schema / properties / timeout_hint / description

Previous value: -"Optional client-side timeout hint in milliseconds (1000–55000). Defaults to server-configured SPARQL_QUERY_TIMEOUT_MS (55000). Virtuoso hard limit is 60 seconds."New value: +"Optional client-side timeout for this request, in milliseconds (1000–55000). When omitted, the server-configured default (SPARQL_QUERY_TIMEOUT_MS, 55000) applies. Virtuoso hard limit is 60 seconds."

First observedJun 7, 2026

TDQS

A4.8/5.0

Behavior5/5

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

The description goes well beyond the readOnlyHint=true annotation by disclosing exactly what happens at execution: non-SELECT forms are rejected before execution, results are capped, and prefixes are auto-injected. This gives the agent concrete expectations about tool behavior and limitations without contradicting any annotation.

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

Conciseness5/5

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

The main description is three dense sentences, all informative, with the core behavior front-loaded. The parameter description is long but every sentence earns its place by explaining real query-writing pitfalls. No filler or redundancy.

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 raw SPARQL tool with high complexity, the description plus schema fully covers what an agent needs: accepted query forms, prefix injection, result limits, important CDM predicates, literal typing pitfalls, and timeout behavior. The presence of an output schema means the description does not need to explain return values. Sibling differentiation is handled through the 'curated tools' framing.

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

Parameters5/5

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

Schema coverage is 100%, and the sparql_query parameter description adds substantial semantic value: it documents key CDM predicates, explains the CELEX typed-literal requirement with an example, warns about FILTER performance, and recommends bif:contains for text. This is far more useful than the raw schema would be on its own.

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?

The description is specific: it names the verb (run), the resource (raw SPARQL SELECT against the CELLAR Virtuoso endpoint), and the purpose (escape hatch for CDM ontology traversals that curated tools do not cover). It clearly distinguishes itself from the sibling eurlex_* tools by describing itself as raw and not curated.

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 description clearly states when to use the tool: when curated tools do not cover CDM ontology traversals. It also sets hard usage constraints: only SELECT is accepted, update forms and ASK/CONSTRUCT/DESCRIBE are rejected, and results are capped at 100. It does not explicitly name alternative sibling tools, but the contrast with 'curated tools' is clear enough.

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

All eur-lex-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.

Raw CELLAR SPARQL Query

Input Schema

Output Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources