beam_search_reasoning

Optimize multi-step reasoning by maintaining top paths through beam search, enabling structured problem-solving and decision-making for complex queries.

Input Schema

Name	Required	Description
`beamWidth`	No	Number of top paths to maintain (n-sampling)
`nextThoughtNeeded`	Yes	Whether another step is needed
`prompt`	Yes	The problem or query to reason about
`thought`	Yes	Current reasoning step
`thoughtNumber`	Yes	Current step number
`totalThoughts`	Yes	Total expected steps

Input Schema (JSON Schema)

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "beamWidth": {
      "default": 3,
      "description": "Number of top paths to maintain (n-sampling)",
      "maximum": 10,
      "minimum": 1,
      "type": "integer"
    },
    "nextThoughtNeeded": {
      "description": "Whether another step is needed",
      "type": "boolean"
    },
    "prompt": {
      "description": "The problem or query to reason about",
      "type": "string"
    },
    "thought": {
      "description": "Current reasoning step",
      "type": "string"
    },
    "thoughtNumber": {
      "description": "Current step number",
      "minimum": 1,
      "type": "integer"
    },
    "totalThoughts": {
      "description": "Total expected steps",
      "minimum": 1,
      "type": "integer"
    }
  },
  "required": [
    "prompt",
    "thought",
    "thoughtNumber",
    "totalThoughts",
    "nextThoughtNeeded"
  ],
  "type": "object"
}

MCP Advanced Reasoning Server

Input Schema

Input Schema (JSON Schema)

Other Tools from MCP Advanced Reasoning Server

Related Tools

MCP directory API