Ingest Mendelian randomization summary statistics from OpenGWAS/IEU-MR and emit causal_link artifact rows.
Runtime config
show config
{
"skill_name": "mr_ingest",
"timeout_secs": 300
}Input schema
JSON Schema
{
"type": "object",
"required": [
"phenotype_query"
],
"properties": {
"limit": {
"type": "integer",
"default": 50,
"maximum": 1000,
"minimum": 1,
"description": "Maximum number of GWAS studies to return per query."
},
"mr_types": {
"type": "array",
"items": {
"enum": [
"bi-directional MR",
"colocalization",
"Mendelian randomization",
"polygenic risk score"
],
"type": "string"
},
"default": [
"Mendelian randomization"
],
"description": "MR study types to include from OpenGWAS."
},
"phenotype_query": {
"type": "string",
"description": "Free-text phenotype or disease name to search for in OpenGWAS (e.g. \"Alzheimer's disease\")."
}
}
}Output schema
JSON Schema
{
"type": "object",
"properties": {
"errors": {
"type": "integer",
"description": "Number of studies that failed to ingest."
},
"skipped": {
"type": "integer",
"description": "Number of studies skipped (no gene symbol, duplicates, etc.)."
},
"took_ms": {
"type": "integer",
"description": "Wall-clock time for the ingestion in milliseconds.\""
},
"ingested": {
"type": "integer",
"description": "Number of causal_link artifact rows created or updated."
},
"causal_link_ids": {
"type": "array",
"items": {
"type": "string"
},
"description": "IDs of the created causal_link artifacts."
}
}
}Invoke
Schema-driven form. Same surface agents call via scidex.tool.invoke.
Posting as anonymous. Sign in for attribution in the audit journal.
Examples
Ingest MR summary statistics for Alzheimer's disease from OpenGWAS.
input
{
"limit": 20,
"phenotype_query": "Alzheimer's disease"
}for agents scidex.tool.invoke
Invoke this tool from an agent. Required arg shape is the input_schema above; the runtime dispatches via skill_call sandboxed under sandbox_backend=<bwrap>. Returns a tool_result envelope with the canonical render_hints applied.
POST /api/scidex/rpc
{
"verb": "scidex.tool.invoke",
"args": {
"name": "mr_ingest",
"args": {}
}
}