Document AI reasoning and decision-making for audit trails. Log analysis, plans, and observations without altering code.
MIT
759,132 tools. Updated 2026-11-08 21:12
"Tools for slow thinking, step-back reasoning, and contextual memory capabilities" matching MCP tools:
- List the authenticated tenant's retained Quantum Reasoning Lab jobs and capabilities with paginated metadata, status filters, and cursor paging, without creating or changing jobs.Apache 2.0
- Inspect debug-log timing (latency, tokens, reasoning) and session-store verdict agreement, then suggest tuning such as disabling slow models or trimming fanout.MIT
- Delegate complex tasks to Claude for code generation, reasoning, and engineering. Include all context in the prompt, as Claude has no conversation memory.MIT
- Consult a reasoning model to receive a complete reasoning trace for multi-step problems. Apply the trace to guide and verify your own answer.MIT
- Analyze complex problems through sequential thinking, track assumptions, and manage multi-step reasoning with confidence scoring and session-based context.MIT
Matching MCP Servers
- AlicenseBqualityDmaintenanceProvides computational tools for systematic reasoning, including boolean evaluation, date arithmetic, object counting, state tracking, and format validation, to enhance agent capabilities and eliminate calculation errors in reasoning tasks.74MIT
- FlicenseNot gradedqualityBmaintenancePersistent memory for AI coding agents: local-first semantic search, dependency graphs, git history.1-
Matching MCP Connectors
- Pryzm MemoryOAuth
Encrypted long-term memory shared across your AI assistants (Claude, ChatGPT, Perplexity).
Deterministic company, entity and location lookups for agents - per call, x402 or API key.
- Access the complete Astria operating guide to learn available tools, recommended workflows, and best practices for persistent memory management.MIT
- Replace a previous thought with updated reasoning, preserving the original in revision history. Corrects incomplete or wrong thinking.MIT
- Check for a newer version of the Memory MCP server. Provides step-by-step update instructions without making any changes.MIT
- Break down complex questions via step-by-step reasoning with web-grounding and numbered citations. For math, logic, comparisons, and chain-of-thought.MIT
- 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
- Start a named thinking chain to guide multi-step reasoning, routing to master when no custom chain matches. Use default or custom chains for freeform or checklist-based problem-solving.MIT
- Toggle ask-fable reasoning-trace capture and live thinking at runtime. Persist trace_mode (full/safe) and stream_reasoning settings without editing config files or restarting.MIT
- Attach a memory to a specific diagram step so notes, anti-patterns, or reasoning explain why that step exists.MITDestructive
- Apply step-by-step reasoning with web grounding to complex questions. Ideal for math, logic, comparisons, and multi-step arguments. Returns reasoned answers with numbered citations. Supports recency, domain, and search context filters.MIT
- Verify a multi-step reasoning chain and return a certificate summary including verdict, confidence score, and pinpointed failures. Use to structurally check reasoning before finalizing an answer.MIT
- Record each step of a reasoning process by adding numbered thoughts to a persistent chain. Ideal for analysis, debugging, design, and research tasks that require structured, sequential thinking.MIT
- Break down complex questions with step-by-step web-grounded reasoning and numbered citations. Supports recency, domain, and search context filters for math, logic, comparisons, and arguments.MIT
- Access documentation and usage guides for n8n workflow automation tools to understand available capabilities and implementation methods.MIT
- Reads and returns the current thinking profile from the system configuration, automatically falling back to default values if the file is missing.AGPL 3.0
- Export the current thinking chain as markdown or JSON. Optionally export a single branch. Use for sharing reasoning with humans or other systems.MIT