HAL Open Archive Document Search by Title Words (dataHAL)
halsparql/document-search
Searches the HAL open archive (the French national repository of research papers, theses and conference papers run by the CCSD) for documents of one type whose title contains all the given words, through dataHAL. Returns up to 100 matches with the document identifier (a data.archives-ouvertes.fr/document/hal-... address) and title. Pass an identifier to document-record for the full record. Matching is by full-text word, not by author or abstract. The service answers at data.hal.science/sparql (the older data.archives-ouvertes.fr/sparql address redirects there). HAL data, served by Eden Engine; not an official HAL or CCSD product.
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
Data from HAL, the French open archive of the Centre pour la Communication Scientifique Directe (CCSD), via dataHAL (data.hal.science). Served by Eden Engine; not an official HAL or CCSD product.
Use it
Five steps: search, inspect, learn, run, settle. No per-tool setup; your agent reaches this tool through the meta-tools it already has.
Connect once and your AI can find and run this tool, and any other it needs.
// 1. search: find the tool
omnial_search({ query: "what you need" })
// 2. inspect: price and input schema
omnial_inspect({ tool: "halsparql/document-search" })
// 3. learn: read the usage guide at runtime
omnial_learn({ tool: "halsparql/document-search" })
// 4. run: price the exact call first, then run it
omnial_execute({ tool: "halsparql/document-search", input: { /* see input_schema */ }, dry_run: true })
omnial_execute({ tool: "halsparql/document-search", input: { /* ... */ } })
// 5. settle: the call is charged when it finishes, nothing to doNot 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.
| Charge | Price |
|---|---|
Per call | $0.0026 |
- Updated
- Oct 24, 2026
Input and output schemas
Input schema
{
"type": "object",
"required": [
"terms",
"document_type",
"limit"
],
"properties": {
"limit": {
"type": "integer",
"maximum": 100,
"minimum": 1,
"description": "Number of matches to return, 1 to 100."
},
"terms": {
"type": "string",
"pattern": "^[A-Za-z0-9 ]{2,100}$",
"description": "Title words, letters and digits separated by spaces, 2 to 100 characters. All words must appear. For example: graphene superconductivity."
},
"document_type": {
"enum": [
"Article",
"ConferencePaper",
"Chapter",
"DoctoralThesis",
"Report",
"Image"
],
"type": "string",
"description": "Kind of document: Article, ConferencePaper, Chapter, DoctoralThesis, Report or Image."
}
},
"additionalProperties": false
}Output schema
{
"type": "object",
"required": [
"head",
"results"
],
"properties": {
"head": {
"type": "object",
"properties": {
"vars": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": true
},
"results": {
"type": "object",
"required": [
"bindings"
],
"properties": {
"bindings": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
},
"description": "One object per result row; each variable maps to {type, value} plus xml:lang or datatype where the value has one."
}
},
"additionalProperties": true
}
},
"description": "The SPARQL 1.1 JSON results document.",
"additionalProperties": true
}