Dual-Cycle Reasoner
This MCP server implements a dual-cycle metacognitive reasoning framework for autonomous agents, built by CyqleLabs using TypeScript with advanced loop detection and recovery mechanisms. The implementation combines statistical anomaly detection, semantic analysis using Hugging Face transformers, and case-based reasoning to identify when agents get stuck in repetitive behaviors like endless scrolling or clicking patterns, then automatically diagnoses failure causes and generates recovery strategies. Built with three core detection strategies (action pattern analysis, state invariance tracking, and progress stagnation detection), belief revision capabilities, and a case-based learning system that adapts from past experiences, it serves developers building autonomous web agents, teams needing robust loop prevention for browser automation tasks, and researchers working on self-monitoring AI systems that can break out of unproductive behavioral cycles.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- browser-automation
- Source
- PulseMCP
- Repository
- github.com/cyqlelabs/mcp-dual-cycle-reasoner
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Dual-Cycle Reasoner from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.