io.github.daedalus/mcp-sparql

Execute a SPARQL SELECT query against a SPARQL endpoint. Runs a SELECT query and returns results as a Markdown table or JSON array. Supports custom HTTP headers for authenticated endpoints. For long-running queries (large datasets, complex joins), increase the timeout parameter — default is 30s, maximum is 3600s (1 hour). Args: params: Query parameters including endpoint URL, SPARQL query, timeout, output format, optional headers, and max rows limit. Returns: Query results formatted as a Markdown table or JSON string. Examples: >>> # Query Wikidata for items >>> sparql_query(SparqlQueryInput( ... endpoint="https://query.wikidata.org/sparql", ... query="SELECT ?item ?itemLabel WHERE { ?item wdt:P31 wd:Q5 . ?item rdfs:label ?itemLabel . FILTER(LANG(?itemLabel) = 'en') } LIMIT 5" ... )) "| `item` | `itemLabel` | | --- | --- | | `http://www.wikidata.org/entity/Q5` | `human` | ..." >>> # Query with authentication >>> sparql_query(SparqlQueryInput( ... endpoint="https://my-endpoint.example.com/sparql", ... query="SELECT ?s ?p ?o WHERE { ?s ?p ?o } LIMIT 10", ... headers={"Authorization": "Bearer my-token"} ... ))

Execute a SPARQL ASK query and return a boolean result. ASK queries test whether a pattern exists in the data, returning true or false. Args: params: Query parameters including endpoint URL, SPARQL ASK query, timeout, and optional headers. Returns: "true" if the pattern exists, "false" otherwise. Examples: >>> # Check if a specific item exists >>> sparql_ask(SparqlAskInput( ... endpoint="https://query.wikidata.org/sparql", ... query="ASK { wd:Q42 wdt:P31 wd:Q5 }" ... )) "true" >>> # Check if a relationship exists >>> sparql_ask(SparqlAskInput( ... endpoint="https://query.wikidata.org/sparql", ... query="ASK { wd:Q42 wdt:P27 wd:Q142 }" ... )) "true"

Execute a SPARQL CONSTRUCT query and return RDF triples. CONSTRUCT queries build an RDF graph from a template pattern. Results are returned as Turtle RDF or JSON-LD. For large-scale graph construction, increase the timeout parameter — default is 30s, maximum is 3600s (1 hour). Args: params: Query parameters including endpoint URL, SPARQL CONSTRUCT query, timeout, output format, optional headers, and max rows limit. Returns: RDF triples formatted as Turtle or JSON. Examples: >>> # Construct a subgraph >>> sparql_construct(SparqlConstructInput( ... endpoint="https://query.wikidata.org/sparql", ... query="CONSTRUCT { wd:Q42 rdfs:label ?name } WHERE { wd:Q42 rdfs:label ?name . FILTER(LANG(?name) = 'en') }" ... )) "@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .\n..."

Execute a SPARQL DESCRIBE query and return an RDF resource description. DESCRIBE queries return an RDF graph describing the specified resource(s). For resources with many properties, increase the timeout parameter — default is 30s, maximum is 3600s (1 hour). Args: params: Query parameters including endpoint URL, SPARQL DESCRIBE query, timeout, output format, optional headers, and max rows limit. Returns: RDF description formatted as Turtle or JSON. Examples: >>> # Describe a Wikidata entity >>> sparql_describe(SparqlDescribeInput( ... endpoint="https://query.wikidata.org/sparql", ... query="DESCRIBE wd:Q42" ... )) "@prefix ...> .\n<...> ..."

Validate SPARQL query syntax without executing it. Parses the query and reports whether it is syntactically valid. Useful for debugging query errors before running them against an endpoint. Args: params: Validation parameters containing the SPARQL query string. Returns: Validation result with status and error details if invalid. Examples: >>> # Valid query >>> sparql_validate(SparqlValidateInput(query="SELECT ?s WHERE { ?s ?p ?o }")) "Valid SPARQL query." >>> # Invalid query >>> sparql_validate(SparqlValidateInput(query="SELECT WHERE { }")) "Invalid SPARQL query: ..."

List available named graphs on a SPARQL endpoint. Queries the endpoint for all named graphs (contexts) available for querying. Args: params: Parameters including endpoint URL, timeout, and optional headers. Returns: List of named graph URIs. Examples: >>> sparql_list_graphs(SparqlListGraphsInput( ... endpoint="https://query.wikidata.org/sparql" ... )) "Found 3 named graphs:\n1. http://example.org/graph1\n..."

Get commonly used prefixes for a SPARQL endpoint. Returns a combination of well-known standard prefixes (rdf, rdfs, owl, xsd, etc.) and any endpoint-specific prefixes discovered via the data. Args: params: Parameters including endpoint URL, timeout, and optional headers. Returns: Formatted list of prefix declarations for use in SPARQL queries. Examples: >>> sparql_get_prefixes(SparqlGetPrefixesInput( ... endpoint="https://query.wikidata.org/sparql" ... )) "PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>\n..."