nexus_similarity_search_api_rank_items_by_nmi_cosine_fusion
ActiveTool of io.github.nexus-mcp-infra/similarity-search-api-sdk
Ranks a corpus of items against a query vector using a calibrated fusion score (alpha * cosine + (1-alpha) * NMI_normalizado), where alpha is auto-derived from the corpus's marginal entropy unless overridden. Results are identified by their 0-indexed position in corpus_vectors (this tool does not accept explicit item IDs). Use this when you need semantically-calibrated similarity over a stateless corpus of up to 500k items without a vector database. Do NOT use for purely geometric nearest-neighbor search where NMI overhead is unnecessary, nor for corpora larger than 500k items per call. Requires a valid api_key (same as X-API-Key) and an x402 payment.
Parameters schema
{
"type": "object",
"title": "rank_items_by_nmi_cosine_fusionArguments",
"required": [
"query_vector",
"corpus_vectors",
"api_key"
],
"properties": {
"top_k": {
"type": "number",
"title": "Top K",
"default": 10,
"maximum": 1000,
"minimum": 1,
"description": "Number of top-ranked results to return, ordered by descending fusion score. Capped at 1000 by the core service regardless of corpus size."
},
"n_bins": {
"type": "number",
"title": "N Bins",
"default": 16,
"maximum": 50,
"minimum": 3,
"description": "Number of histogram bins used to discretize continuous dimensions when estimating NMI. Must be between 3 and 50."
},
"api_key": {
"type": "string",
"title": "Api Key",
"description": "API key required for this paid operation -- same secret configured as X-API-Key on the REST endpoints (SIMILARITY_API_KEY). Payment (x402) alone is not sufficient; both gates must pass."
},
"query_vector": {
"type": "array",
"items": {
"type": "number"
},
"title": "Query Vector",
"maxItems": 4096,
"minItems": 2,
"description": "Dense numeric vector representing the query item. Must have the same dimensionality as all corpus_vectors entries."
},
"alpha_override": {
"type": "number",
"title": "Alpha Override",
"default": null,
"maximum": 1,
"minimum": 0,
"description": "Fixed alpha weight for cosine component in [0.0, 1.0]. If omitted, alpha is auto-calibrated from corpus entropy. Set to 1.0 to use pure cosine; 0.0 for pure NMI."
},
"corpus_vectors": {
"type": "array",
"items": {
"type": "array",
"items": {
"type": "number"
}
},
"title": "Corpus Vectors",
"maxItems": 500000,
"minItems": 1,
"description": "List of dense numeric vectors forming the corpus to rank against. Each inner array must match query_vector dimensionality. Maximum 500000 entries."
}
}
}Parent server
io.github.nexus-mcp-infra/similarity-search-api-sdk
https://github.com/nexus-mcp-infra/similarity-search-api-sdk
1/7 registries