Stateless NMI + cosine fusion with entropy-driven alpha calibration
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Computes the aggregate entropy-calibrated alpha for a corpus without running a full search -- useful to inspect before committing to a large rank_items_by_nmi_cosine_fusion call. Returns a single aggregate corpus_entropy value, NOT a per-dimension breakdown -- the real logic only exposes the mean marginal entropy across dimensions, not H(X_d) per individual dimension. Do NOT use expecting per-dimension granularity. Requires an x402 payment.
List of dense numeric vectors for which to compute the aggregate entropy and calibrated alpha. Each inner array must be the same length. Maximum 500000 entries.
Number of histogram bins for entropy discretization. Must be between 3 and 50; should match the n_bins used in rank_items_by_nmi_cosine_fusion for the profile to be consistent.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Computes the aggregate entropy-calibrated alpha for a corpus without running a full search -- useful to inspect before committing to a large rank_items_by_nmi_cosine_fusion call. Returns a single aggregate corpus_entropy value, NOT a per-dimension breakdown -- the real logic only exposes the mean marginal entropy across dimensions, not H(X_d) per individual dimension. Do NOT use expecting per-dimension granularity. Requires an x402 payment.
| Argument | Type | Description |
|---|---|---|
| n_bins | number | Number of histogram bins for entropy discretization. Must be between 3 and 50; should match the n_bins used in rank_items_by_nmi_cosine_fusion for the profile to be consistent. |
| corpus_vectors* | array | List of dense numeric vectors for which to compute the aggregate entropy and calibrated alpha. Each inner array must be the same length. Maximum 500000 entries. |
{
"type": "object",
"title": "estimate_corpus_entropy_profileArguments",
"required": [
"corpus_vectors"
],
"properties": {
"n_bins": {
"type": "number",
"title": "N Bins",
"default": 16,
"maximum": 50,
"minimum": 3,
"description": "Number of histogram bins for entropy discretization. Must be between 3 and 50; should match the n_bins used in rank_items_by_nmi_cosine_fusion for the profile to be consistent."
},
"corpus_vectors": {
"type": "array",
"items": {
"type": "array",
"items": {
"type": "number"
}
},
"title": "Corpus Vectors",
"maxItems": 500000,
"minItems": 1,
"description": "List of dense numeric vectors for which to compute the aggregate entropy and calibrated alpha. Each inner array must be the same length. Maximum 500000 entries."
}
}
}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 an x402 payment.
| Argument | Type | Description |
|---|---|---|
| top_k | number | 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 | number | Number of histogram bins used to discretize continuous dimensions when estimating NMI. Must be between 3 and 50. |
| query_vector* | array | Dense numeric vector representing the query item. Must have the same dimensionality as all corpus_vectors entries. |
| alpha_override | number | 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* | array | List of dense numeric vectors forming the corpus to rank against. Each inner array must match query_vector dimensionality. Maximum 500000 entries. |
Computes the NMI-cosine fusion score for exactly one (query, target) vector pair at a fixed alpha. Use for explainability, debugging, or unit-level validation of fusion scores before running full corpus ranking. Unlike corpus-level ranking, alpha is NOT auto-calibrated for a single pair -- the real logic requires a fixed alpha (default 0.5); pass alpha explicitly for a specific blend. Do NOT use in a loop to score many pairs; batch them into rank_items_by_nmi_cosine_fusion instead. Requires an x402 payment.
| Argument | Type | Description |
|---|---|---|
| alpha | number | Fixed alpha weight for the cosine component in [0.0, 1.0], applied as-is -- not auto-calibrated. Default 0.5 matches the core service default. |
| n_bins | number | Histogram bins for NMI discretization. Must be between 3 and 50. |
| vector_a* | array | First dense numeric vector of the pair. Must have the same dimensionality as vector_b. |
| vector_b* | array | Second dense numeric vector of the pair. Must have the same dimensionality as vector_a. |
{
"type": "object",
"title": "score_pair_nmi_cosineArguments",
"required": [
"vector_a",
"vector_b"
],
"properties": {
"alpha": {
"type": "number",
"title": "Alpha",
"default": 0.5,
"maximum": 1,
"minimum": 0,
"description": "Fixed alpha weight for the cosine component in [0.0, 1.0], applied as-is -- not auto-calibrated. Default 0.5 matches the core service default."
},
"n_bins": {
"type": "number",
"title": "N Bins",
"default": 16,
"maximum": 50,
"minimum": 3,
"description": "Histogram bins for NMI discretization. Must be between 3 and 50."
},
"vector_a": {
"type": "array",
"items": {
"type": "number"
},
"title": "Vector A",
"maxItems": 4096,
"minItems": 2,
"description": "First dense numeric vector of the pair. Must have the same dimensionality as vector_b."
},
"vector_b": {
"type": "array",
"items": {
"type": "number"
},
"title": "Vector B",
"maxItems": 4096,
"minItems": 2,
"description": "Second dense numeric vector of the pair. Must have the same dimensionality as vector_a."
}
}
}{
"type": "object",
"title": "rank_items_by_nmi_cosine_fusionArguments",
"required": [
"query_vector",
"corpus_vectors"
],
"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."
},
"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."
}
}
}