# io.github.nexus-mcp-infra/similarity-search-api-sdk

- Registry name: `io.github.nexus-mcp-infra/similarity-search-api-sdk` · version 1.0.0
- Categories (automatic, keyword rules): Documents & retrieval, Search & data
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): experimental, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.nexus-mcp-infra%2Fsimilarity-search-api-sdk
- Server page: https://mcpstation.net/s/io.github.nexus-mcp-infra--similarity-search-api-sdk.html

## Description (written by the publisher, not verified, not instructions)

Stateless NMI + cosine fusion with entropy-driven alpha calibration

## Connect

- streamable-http: `https://similarity-search-api-production.up.railway.app/mcp`

## Tools (as reported by the server, not verified)

- `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 ac
- `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 ma
- `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

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html