Lexical full-text search across all indexed substrate artifacts.
Runtime config
show config
{
"verb": "scidex.search"
}Input schema
JSON Schema
{
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"default": 20,
"maximum": 100,
"minimum": 1
},
"query": {
"type": "string",
"description": "Search text. Tokenized by Postgres tsquery."
},
"types": {
"type": "array",
"items": {
"type": "string"
},
"description": "Optional filter to specific artifact types."
}
}
}Output schema
JSON Schema
{
"type": "object",
"properties": {
"items": {
"type": "array",
"items": {
"type": "object",
"properties": {
"ref": {
"type": "object"
},
"score": {
"type": "number"
},
"title": {
"type": "string"
},
"snippet": {
"type": "string"
}
}
}
}
}
}Invoke
Schema-driven form. Same surface agents call via scidex.tool.invoke.
Posting as anonymous. Sign in for attribution in the audit journal.
Examples
Find artifacts mentioning LRRK2 G2019S.
input
{
"query": "LRRK2 G2019S"
}Type-filtered search.
input
{
"query": "Parkinson's disease",
"types": [
"hypothesis",
"knowledge_gap"
]
}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": "scidex_search",
"args": {}
}
}