run_hypothesis_tournament

Identify root causes of code issues by running a competitive hypothesis tournament. Multiple AI conversations test and score theories in parallel, narrowing down solutions through evidence-based elimination rounds.

Instructions

Run a competitive hypothesis tournament to find root causes. Multiple AI conversations test different theories in parallel, with evidence-based scoring and elimination rounds.

Input Schema

Name	Required	Description
`claude_context`	Yes
`issue`	Yes	Description of the issue to investigate
`tournament_config`	No

Input Schema (JSON Schema)

{
  "properties": {
    "claude_context": {
      "properties": {
        "attempted_approaches": {
          "description": "What Claude Code already tried",
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        "code_scope": {
          "properties": {
            "entry_points": {
              "description": "Specific functions/methods to start from",
              "type": "array"
            },
            "files": {
              "description": "Files to analyze",
              "items": {
                "type": "string"
              },
              "type": "array"
            },
            "service_names": {
              "description": "Services involved in cross-system analysis",
              "items": {
                "type": "string"
              },
              "type": "array"
            }
          },
          "required": [
            "files"
          ],
          "type": "object"
        },
        "partial_findings": {
          "description": "Any findings Claude Code discovered",
          "type": "array"
        },
        "stuck_description": {
          "description": "Description of where Claude Code got stuck",
          "type": "string"
        }
      },
      "required": [
        "attempted_approaches",
        "partial_findings",
        "stuck_description",
        "code_scope"
      ],
      "type": "object"
    },
    "issue": {
      "description": "Description of the issue to investigate",
      "type": "string"
    },
    "tournament_config": {
      "properties": {
        "max_hypotheses": {
          "description": "Number of initial hypotheses to generate (default: 6)",
          "maximum": 20,
          "minimum": 2,
          "type": "number"
        },
        "max_rounds": {
          "description": "Maximum tournament rounds (default: 3)",
          "maximum": 5,
          "minimum": 1,
          "type": "number"
        },
        "parallel_sessions": {
          "description": "Max concurrent conversations (default: 4)",
          "maximum": 10,
          "minimum": 1,
          "type": "number"
        }
      },
      "type": "object"
    }
  },
  "required": [
    "claude_context",
    "issue"
  ],
  "type": "object"
}

Deep Code Reasoning MCP Server

run_hypothesis_tournament

Instructions

Input Schema

Input Schema (JSON Schema)

Other Tools from Deep Code Reasoning MCP Server

Related Tools

MCP directory API