"Tools for slow thinking, step-back reasoning, and contextual memory capabilities" matching MCP servers:

Enables MCP clients to perform step-level process reward evaluation, MCTS-guided reasoning search, hallucination branch pruning, and formal verification for complex math, code, and logic problems.

Enables agents to verify complex math, code, and logic reasoning through MCTS step-level process reward modeling, counterfactual backtracking, symbolic proof checking, and majority-vote consensus so hallucinated branches get pruned. It also allocates test-time compute dynamically and exposes these capabilities over a zero-dependency STDIO MCP server for Claude Desktop, Cursor, and other agent runtimes.

MCP server for step-by-step mathematical reasoning and planning, enabling AI agents to execute calculations and perform GUI actions like opening PowerPoint.

Provides RAG (Retrieval-Augmented Generation) capabilities via Contextual AI, enabling query processing and context-aware responses with citations. Integrates with MCP clients like Cursor IDE and Claude Desktop.

A powerful MCP server that enhances LLMs with advanced sequential thinking capabilities, supporting 19 thinking modes for structured reasoning and complex cognitive tasks.

Adds a deep_reasoning tool that consults stronger reasoning models (e.g., DeepSeek R1) to produce full reasoning traces for complex problems, helping the agent shape and cross-check its answers.

A local MCP server that integrates Step Plan API for image generation and text-to-speech, allowing MCP-compatible clients like Codex to use these capabilities without switching models.

Provides AI systems with structured thinking frameworks and reasoning tools to maintain consistent problem-solving patterns across conversations. Enables multi-step reasoning, decision analysis, and systematic troubleshooting through invocable mental models.

An MCP server that enhances sequential thinking with Ultra Think methodology, enabling structured, step-by-step reasoning with quality metrics, bias detection, and resource management.

Enables AI agents to drive policy evaluation over MCP by starting executions, answering policy questions from case evidence, and reading deterministic outcomes with reasoning traces, while the runtime controls which questions are asked and how answers combine.

Enables multi-step AI reasoning by sending prompts to OpenRouter, performing a verification pass, and returning both responses with provider reasoning fields when available.

An MCP server for downloading and reading MGX thinking logs, enabling AI agents to fetch and analyze MGX conversation logs programmatically.

Enables Claude Code to escalate complex code analysis to Google's Gemini AI for multi-model reasoning, including execution tracing, cross-system impact analysis, performance bottleneck detection, and hypothesis testing over large codebases and logs.

Provides reasoning budget estimates for AI tasks, making effort and time trade-offs visible through a compact control interface.

A self-hosted MCP server that provides tools for structured reasoning, confidence calibration, and detecting recurring gaps in AI outputs, aiming to reduce workload by improving verification and attention allocation.

MCP server for deep algorithmic and mathematical reasoning, wrapping any OpenAI-compatible LLM endpoint to return only the final distilled answer without reasoning traces. Supports per-call model and endpoint overrides, defaulting to vibethinker-3b via LM Studio.

Enables AI agents to perform dynamic and reflective problem-solving through a chain of thoughts, allowing them to break down complex problems, revise past thoughts, and explore logic branches before reaching a conclusion.

A structured problem-solving MCP server that breaks down complex tasks into sequential steps, supports iterative refinement and branching, and helps maintain context and explore alternative reasoning paths.

Provides a sequentialthinking tool for dynamic, reflective problem-solving via chain-of-thought reasoning. Supports local Stdio and remote SSE deployment on Google Cloud Run.

Enables agents to audit their own reasoning trajectories for loops, deadlocks, and logical contradictions, then perform non-destructive checkpoint rollbacks to a sound prior step. It combines step-level reward evaluation, MCTS search, symbolic proof checking, and consensus voting to return verified solutions over MCP stdio.

A stateless remote MCP server that lets AI agents anonymously submit encrypted reports of alignment and safety failures to leaks.md (what others did) and confession.md (what the agent itself did), returning a receipt without accounts or keys. It exposes public tools such as submit_leak and submit_confession over Streamable HTTP.

Persistent memory storage using SQLite for AI agents to store, search, update, and manage contextual memory via the Model Context Protocol.

Enables Claude Code and other MCP clients to escalate complex code investigations to Google's Gemini AI for large-context trace analysis, cross-service impact assessment, performance bottleneck detection, hypothesis testing, and multi-turn AI-to-AI debugging.

Enables Claude Code to escalate complex code analysis to Gemini for long-context debugging, execution tracing, cross-system impact analysis, performance modeling, and hypothesis testing, including AI-to-AI multi-turn conversations. It supports analyzing large logs, traces, and codebases by leveraging Gemini's 1M-token context window and code execution capabilities.

Provides a collection of MCP servers for computational chemistry tasks including molecular generation and retrosynthesis. Also offers property prediction and molecule pricing capabilities.

Enables dynamic and reflective problem-solving through a structured thinking process, breaking down complex problems into manageable steps with revision and branching capabilities.

Enables Claude Code to escalate complex analysis to Gemini for multi-model reasoning over large codebases, logs, and traces, with capabilities for execution-flow tracing, cross-system impact analysis, performance bottleneck detection, hypothesis testing, and iterative AI-to-AI dialogue.

Enables Claude Code to escalate complex code analysis tasks to Gemini for large-context reasoning, execution-flow tracing, cross-system impact analysis, performance bottleneck detection, and hypothesis testing, including AI-to-AI conversational analysis.

Provides Dify apps with a secure, app-scoped MCP tool catalog and action gateway for authorized FlowFlox operations, enabling intent-driven planning and fixed operational processes without exposing global credentials.

Enables Claude Code to escalate complex analysis tasks to Google's Gemini AI, which handles large-context reasoning, execution flow tracing, cross-system impact analysis, performance bottleneck detection, and hypothesis testing. It also supports multi-turn AI-to-AI conversational sessions for iterative debugging of distributed systems and long trace logs.