"Slow thinking, distributed thinking, and reasoning abilities research" matching MCP tools:

• pplx_claude_opus_thinkC

  Perplexity Web MCPB

  Run advanced reasoning queries with Perplexity using Claude Opus 4.8 extended thinking. Requires Max subscription, uses 1 Pro search credit.

  MIT

• deep_thinkingA

  win-cli-mcp-tmyyB

  Break down complex problems into manageable steps, revise reasoning as understanding deepens, and explore alternative paths through structured sequential thinking.

  -

• create_thinking_chainC

  Hi-AIC

  Generate sequential reasoning chains to structure complex thinking processes by breaking topics into logical steps for clearer analysis.

  MIT

• create_thinking_chainC

  Hi-AIC

  Generate structured reasoning chains to break down complex topics into sequential thinking steps for clearer problem-solving and analysis.

  MIT

• plan_writeA

  Cheap LaborA

  Write a detailed plan file (PLAN.md, SPEC.md, or TASKS.md) with step-by-step instructions so Codex can implement tasks without further thinking. Replaces existing file contents.

  MIT

• turingmind_log_reasoningA

  TuringMind MCP ServerA

  Document AI reasoning and decision-making for audit trails. Log analysis, plans, and observations without altering code.

  MIT

• rct_thinkA

  delentia-sovereignA

  Deconstruct complex problems with a 7-stage reverse thinking process to eliminate hallucination and achieve rigorous reasoning.

  Apache 2.0

• adviseA

  deepseek-mcpA

  Analyze complex, high-stakes decisions using deep reasoning. Returns structured conclusion, reasoning, and risk warnings.

  MIT

• resetA

  MAXential Thinking MCPA

  Clear the in-memory thinking state to start a fresh session while preserving all previous data in SQLite. Requires confirmation to prevent accidental clearing.

  MIT

• gemini_chatA

  Google Gemini MCPA

  Chat with Gemini models for answers, code, research, and AI tasks. Uses Google Search grounding by default for real-time information and supports configurable thinking depth. Send a message to get a response.

  Apache 2.0

• pplx_councilA

  Perplexity Web MCPB

  Query multiple AI models in parallel and receive a synthesized consensus answer. Choose council members, source focus, and extended thinking to fit your research need.

  MIT

• vision_analyze_imageA

  deepseek-vision-mcpA

  Analyze an image from a local path or URL and answer questions about it. Provide a source and a question; optional deep thinking mode yields more detailed responses.

  MIT

• chat_completionA

  DeepSeek MCP ServerA

  Generate single-turn or multi-turn responses with DeepSeek V4. Choose flash or pro models, control thinking, and persist conversation context. Provide a message or full chat history to get AI-generated replies.

  MIT

• ultrathinkA

  UltraThinkA

  Analyze complex problems through sequential thinking, track assumptions, and manage multi-step reasoning with confidence scoring and session-based context.

  MIT

• reviseA

  MAXential Thinking MCPA

  Replace a previous thought with updated reasoning, preserving the original in revision history. Corrects incomplete or wrong thinking.

  MIT

• visualizeA

  MAXential Thinking MCPA

  Generate a diagram of a thinking chain, displaying thoughts, branch points, and revisions in Mermaid or ASCII format for sharing or navigating reasoning structures.

  MIT

• session_saveA

  MAXential Thinking MCPA

  Assign a human-readable name and optional description to the current thinking session. Without this, sessions use auto-generated timestamp names, making them harder to find later.

  MIT

• cassette_configA

  oh-my-cassetteB

  View or change the Cassette model and thinking level for a session. Pass a session ID to see current settings and options, or provide model/thinking level to update them.

  MIT

• report_ai_coach_activityA

  AI Coach MCP ServerA

  Update the AI Coach mascot with your current activity state to trigger animations and speech bubbles for thinking, working, waiting, succeeded, or failed.

  MIT

• sequentialthinkingA

  Sequential-ThinkingA

  Analyze complex problems through adaptive thinking steps that build, question, and revise insights to reach solutions. Supports branching, backtracking, and iterative refinement for dynamic problem-solving.

  Apache 2.0

• sequential_thinkingA

  memory-bank-mcpB

  Record numbered thinking steps for structured reasoning, enabling complex problems to be broken into sequential steps with branching and revision. Manage session history, reset when needed, and finalize to persist outcomes to Memory Bank.

  MIT