rank_documents_by_embedding

Active

declared in 1.0.0

Embed a query and candidate documents, then rank documents by cosine similarity. Use for semantic matching, retrieval checks, clustering triage, and lightweight RAG over user-provided passages.

Parameters schema

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "query",
    "documents",
    "top_k"
  ],
  "properties": {
    "query": {
      "type": "string",
      "maxLength": 4000,
      "minLength": 1
    },
    "top_k": {
      "type": "number",
      "default": 10,
      "maximum": 20,
      "minimum": 1
    },
    "documents": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 8000,
        "minLength": 1
      },
      "maxItems": 30,
      "minItems": 1
    }
  },
  "additionalProperties": false
}

What this tool wraps· 0 endpoints

min confidence0.70 0.50

No endpoints wrapped at confidence ≥ 0.70.

Parent server

Claidex MCP

https://github.com/ssatanis/claidex-sentinel

1/7 registries

View full server →