"thinking" matching MCP servers:

Simple sequential thinking MCP in python

An advanced MCP server that implements sophisticated sequential thinking using a coordinated team of specialized AI agents (Planner, Researcher, Analyzer, Critic, Synthesizer) to deeply analyze problems and provide high-quality, structured reasoning.

This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.

Facilitates structured, step-by-step problem-solving using the Model Context Protocol, ideal for planning complex tasks like supply chain management.

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

A Python-based MCP server that facilitates structured problem-solving through sequential thinking, branching, and confidence scoring. It allows users to track assumptions and manage multiple concurrent reasoning sessions to break down complex tasks.

An open-source deep research MCP server that provides multi-source web search and synthesis with citations, enabling agents to perform citation-backed research using Qwen3-30B-A3B-Thinking and other models.

MCP server for Google's Gemini 3.1 Flash Image that enables fast, high-resolution image generation with advanced reasoning, up to 14 reference images, Google Search grounding, and automatic thinking mode.

MCP server for DeepSeek AI models (Chat + Reasoner). Supports multi-turn sessions, model fallback with circuit breaker, function calling, thinking mode, JSON output, multimodal input, and cost tracking.

Enables personal knowledge management through Claude Desktop, allowing users to capture thoughts, connect ideas, and reflect on thinking changes via natural conversation.

Enables LLMs to break down reasoning into an explicit, editable graph of thinking steps, with visualizations and the ability to revise individual steps.

MCP server for querying Google Gemini Web from Claude Code and other MCP clients, using cookie-based authentication. Enables creating, continuing, listing, viewing, and deleting Gemini chat conversations with model and thinking mode control.

Enables coding agents to consult, design, implement, and review with an independent AI peer via Oh My Pi, using persistent project-isolated conversations and structured MCP tools for thinking, analysis, and authorized work.

Provides access to Brian Eno and Peter Schmidt's Oblique Strategies card deck to help users overcome creative blocks through lateral thinking. It enables searching and retrieving random prompts from various editions, including collections adapted specifically for programmers.

MCP server for knowledge graphs designed around neurodivergent thinking patterns, organizing memories into five districts with BM25 ranking and bidirectional connections.

Enables multi-turn conversations with Google Gemini AI models, supporting file and image analysis, automatic model selection, deep thinking mode, and Google Search integration through the AIStudioProxyAPI backend.

Provides LLMs with cognitive tools (Thinking Models), memory structures (Cells), and multi-agent patterns (Organs) for advanced reasoning, memory management, and orchestration. Automatically routes requests to appropriate strategies and generates custom agent blueprints.

A minimal, token-efficient MCP server that combines stock prices and fundamentals with the macro and micro narrative around them — so an AI agent can reason about why a stock moved, what people are thinking about it, and what probable scenarios lie ahead.

Enables agents to create and drive instrumented Design Thinking sessions, inspect the append-only journal, and retrieve dossiers and handoff specs through MCP tools and resources.

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.