"sequential thinking" matching MCP servers:

Persistent sequential thinking for MCP clients, stored durably on Cloudflare Workers with support for branching, revision, and history retrieval.

An enhanced sequential thinking tool optimized for programming tasks that helps break down complex coding problems into structured, self-auditing thought steps with branching and revision capabilities.

MCP server for structured reasoning with cognitive trap detection, verification, and context compression

Combines structured sequential thinking with batch operation execution, enabling step-by-step reasoning with revision/branching capabilities and chained operations with variable piping between steps.

A unified MCP server for enterprise tool chaining, route optimization, sequential thinking, time management, monitoring, analytics, security, and compliance.

Provides structured thinking with step-by-step reasoning and steel-manning verification for AI agents, backed by cognitive science research.

MCP server that exposes agent-memory-daemon to any MCP-compatible client — Kiro (CLI & IDE), Claude Desktop, Cursor, and others. The daemon does the thinking (consolidation + extraction); this server is a thin filesystem bridge so agents can read, append, and search memory through the Model Context Protocol.

Enables AI agents to speak using MacOS native text-to-speech, with support for blocking and non-blocking speech and a sequential queue.

Enables problem-solving using a structured wisdom framework inspired by the Lotus Sutra, combining analytical thinking with intuitive wisdom through multi-faceted contemplative approaches and meditation pauses.

MindBase implements Karpathy's "LLM wiki" pattern as an MCP server. Instead of retrieving chunks at query time (RAG), the LLM maintains a persistent wiki between your conversations: it reads every source you feed it, cross-references pages with [[wikilinks]], flags contradictions between sources, and keeps a context.md that reflects your current synthesized thinking.

Enables cost-effective repository analysis, code search, file editing, and task planning by wrapping the cursor-agent CLI through focused tools. Reduces token usage by offloading heavy thinking tasks from Claude to specialized operations with configurable output formats.

Enables agents to dynamically schedule thinking-token budgets, reflection passes, and temperature annealing while performing MCTS/process-reward verification, proof checking, and consensus voting through a standard-library STDIO MCP interface.

Enables agents to monitor running loops, estimate token consumption and monetary cost, prune verbose thinking chains near limits, and route sub-tasks between fast/cheap models and deep reasoning engines. It provides budget-aware model routing and telemetry through MCP.

DeepThonk is an MCP server that provides a budget-friendly, provider-neutral deep-thinking engine based on the OpenDeepThink algorithm, enabling agents to plan, run, and inspect multi-round candidate answer generation and ranking tasks with configurable budgets and model providers.