deliberate-reasoning-engine and mcp-structured-thinking
About deliberate-reasoning-engine
haasonsaas/deliberate-reasoning-engine
MCP server that transforms linear AI reasoning into structured, auditable thought graphs
Implements semantic thought categorization (objectives, hypotheses, assumptions, evidence, critiques) as nodes in a directed acyclic graph with explicit dependency tracking and cascade invalidation—when an assumption is disproven, all dependent reasoning automatically becomes stale. Integrates with Claude Desktop via the Model Context Protocol, exposing tools for logging structured thoughts, retrieving the reasoning graph, and invalidating assumptions to maintain reasoning consistency.
About mcp-structured-thinking
Promptly-Technologies-LLC/mcp-structured-thinking
A TypeScript Model Context Protocol (MCP) server to allow LLMs to programmatically construct mind maps to explore an idea space, with enforced "metacognitive" self-reflection
This tool helps Large Language Models (LLMs) systematically explore complex ideas by constructing and managing an evolving mind map. It takes an LLM's raw thoughts and organizes them into stages, assigns quality scores, and enables parallel exploration of different lines of reasoning. The primary users are developers or researchers working with LLMs who need to improve the LLM's ability to structure its thinking process.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work