Skip to content
Eden Engine

Scholarly Knowledge Graph SPARQL SELECT (Open Research Knowledge Graph)

orkg/sparql-select

Runs one read-only SPARQL SELECT over the Open Research Knowledge Graph (ORKG, TIB Leibniz Information Centre for Science and Technology: scholarly papers, contributions, research fields and the structured statements about them) and returns the SPARQL JSON results. The outer query is capped at `limit` rows (default 100, at most 100); write no PREFIX lines and no # comments, so write every IRI in full in angle brackets. The graph is large: filter early, and expect a heavy aggregate to time out. ORKG data, passed through unmodified and served by Eden Engine; not an official ORKG or TIB product.

activeper callv1

Price

$0.0026 per call

You pay the price shown. If a call turns out to cost more than its quote, you pay the actual price, capped at twice the quote. No monthly minimum. Top-ups start at $0.50.

Data source

Open Research Knowledge Graph

Data from the Open Research Knowledge Graph (ORKG), run by the TIB Leibniz Information Centre for Science and Technology (orkg.org), published under CC0 1.0, passed through unmodified. Records that ORKG republished from Papers With Code carry CC BY-SA terms. Served by Eden Engine; not an official ORKG or TIB product.

Use it

Your AI assistant does the work: it finds this tool, shows you the price first, runs it, and you are charged when the run finishes. There is nothing to set up for this tool in particular.

Connect once and your AI can find and run this tool, and any other it needs.

For developers: the calls your assistant makes
agent
// 1. search: find the tool
omnial_search({ query: "what you need" })

// 2. inspect: price and input schema
omnial_inspect({ tool: "orkg/sparql-select" })

// 3. learn: read the usage guide at runtime
omnial_learn({ tool: "orkg/sparql-select" })

// 4. run: price the exact call first, then run it
omnial_execute({ tool: "orkg/sparql-select", input: { /* see input_schema */ }, dry_run: true })
omnial_execute({ tool: "orkg/sparql-select", input: { /* ... */ } })

// 5. settle: the call is charged when it finishes, nothing to do

Not connected yet? Point your MCP client at https://mcp.eden-engine.com/mcp, then copy a config for your client.

Pricing

Every charge this tool can incur.

ChargePrice
Per call
$0.0026
Updated
Oct 28, 2026

Input and output schemas

Input schema
input_schema.json
{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 100,
      "maximum": 100,
      "minimum": 1,
      "description": "Most rows to return, 1 to 100. Default 100."
    },
    "query": {
      "type": "string",
      "pattern": "^(?![\\s\\S]*(?:(?:^|[^A-Za-z?$:])[Ss][Ee][Rr][Vv][Ii][Cc][Ee](?![A-Za-z0-9_.-]*:)|\\\\[uU]))\\s*[Ss][Ee][Ll][Ee][Cc][Tt]\\b(?:[^#<]|<[^<>\\s]*>|<(?=[\\s=]))*$",
      "maxLength": 3000,
      "minLength": 8,
      "description": "One SPARQL SELECT over the ORKG, for example SELECT ?paper ?title WHERE { ?paper a <http://orkg.org/orkg/class/Paper> ; <http://www.w3.org/2000/01/rdf-schema#label> ?title }. Write every IRI in full, no PREFIX lines, no # comments and no SERVICE clause. Put no LIMIT on the outer query: the tool adds one from `limit`. SERVICE clauses and backslash-u/U escapes are refused; the word service is also refused inside string literals, so use a regex on a different spelling or a STR comparison."
    }
  },
  "additionalProperties": false
}
Output schema
output_schema.json
{
  "type": "object",
  "required": [
    "head",
    "results"
  ],
  "properties": {
    "head": {
      "type": "object",
      "properties": {
        "vars": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "The names of the result columns."
        }
      },
      "additionalProperties": true
    },
    "results": {
      "type": "object",
      "required": [
        "bindings"
      ],
      "properties": {
        "bindings": {
          "type": "array",
          "items": {
            "type": "object",
            "additionalProperties": {
              "type": "object",
              "properties": {
                "type": {
                  "type": "string",
                  "description": "uri, literal, typed-literal or bnode."
                },
                "value": {
                  "type": "string"
                },
                "datatype": {
                  "type": "string"
                },
                "xml:lang": {
                  "type": "string"
                }
              },
              "additionalProperties": true
            }
          },
          "description": "One object per result row, keyed by column name; each cell has `type` and `value` (plus `datatype` or `xml:lang` where they apply)."
        }
      },
      "additionalProperties": true
    }
  },
  "additionalProperties": true
}