# similarity-search-api-sdk MCP server

Stateless NMI + cosine fusion with entropy-driven alpha calibration

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-nexus-mcp-infra-similarity-search-api-sdk
- Repository: https://github.com/nexus-mcp-infra/similarity-search-api-sdk

## Install
- Endpoint: https://similarity-search-api-production.up.railway.app/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://similarity-search-api-production.up.railway.app/mcp

## Tools
- nexus_similarity_search_api_rank_items_by_nmi_cosine_fusion - 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. Endpoint: https://similarity-search-api-production.up.railway.app/mcp
- nexus_similarity_search_api_estimate_corpus_entropy_profile - 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 a valid api_key (same as X-API-Key) and an x402 payment. Endpoint: https://similarity-search-api-production.up.railway.app/mcp
- nexus_similarity_search_api_score_pair_nmi_cosine - 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 a valid api_key (same as X-API-Key) and an x402 payment. Endpoint: https://similarity-search-api-production.up.railway.app/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.nexus-mcp-infra
- Version: 1.0.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 17, 2026
- Source: https://registry.modelcontextprotocol.io