Skip to main content
Glama

MCP Dual-Cycle Reasoner

by cyqlelabs
MIT License
158
3

detect_loop

Identify if an agent is stuck in a reasoning loop by analyzing its current context, goal, and chosen detection method (statistical, pattern, or hybrid) to enable intelligent recovery and progress.

Instructions

Detect if the agent is stuck in a loop using various strategies

Input Schema

NameRequiredDescriptionDefault
current_contextNoCurrent environment context or state, in low dash format. Example: sending_email
detection_methodNoLoop detection method to use: statistical, pattern or hybrid.hybrid
goalYesCurrent goal being pursued

Input Schema (JSON Schema)

{ "$schema": "http://json-schema.org/draft-07/schema#", "additionalProperties": false, "properties": { "current_context": { "description": "Current environment context or state, in low dash format. Example: sending_email", "type": "string" }, "detection_method": { "default": "hybrid", "description": "Loop detection method to use: statistical, pattern or hybrid.", "enum": [ "statistical", "pattern", "hybrid" ], "type": "string" }, "goal": { "description": "Current goal being pursued", "type": "string" } }, "required": [ "goal" ], "type": "object" }

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cyqlelabs/mcp-dual-cycle-reasoner'

If you have feedback or need assistance with the MCP directory API, please join our Discord server