- Conduid
- Marketplace
- #reasoning
MCP servers tagged reasoning
59 live MCP servers tagged "reasoning", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with reasoning.
Microsoft Clarity
A Model Context Protocol (MCP) server for Microsoft Clarity
Haft
Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and parity enforcement. For Claude Code, Cursor, Gemini CLI, Codex and mor…
Metacog
mcp tools for llm metacogntition
Cerebro
A model-agnostic MCP Client-Server for .Net and Unity
Agentic AI
Agentic AI research papers, benchmarks, frameworks, and tools curated across 24 domains.
Open Ontologies
AI-native ontology engine: a Rust MCP server with tools for building, validating, querying, and reasoning over RDF/OWL ontologies. In-memory Oxigraph triple store, native OWL2-DL…
Ontosphere
Browser-based RDF/ontology knowledge graph editor — load RDF from files, URLs or SPARQL endpoints; author nodes and edges on the canvas; run OWL-RL reasoning; apply multi-algorith…
Lemoncrow
Faster runtime for coding agents. Make coding agents 25% faster and 30% cheaper on average while keeping the quality same or more. Same Task, Same Quality, Faster and Cheaper.
Wuwe
A framework for building intelligent agents
VSCode Perplexity MCP
Perplexity AI search, reasoning, research, and compute - MCP server, dashboard, and multi-IDE auto-config for VS Code.
Advanced Reasoning MCP
Allows AI to perform advanced reasoning, store the reasoning automatically, and can create system prompts or domain knowledge as libraries.
Deepseek CLI
DeepSeek CLI — Open-source autonomous AI coding agent in your terminal powered by DeepSeek API
Yggdrasil
Reasoning orchestration MCP - Tree of Thoughts with multi-agent evaluation. Fork of Anthropic's sequential-thinking with string coercion fix.
Yggdrasil
Reasoning orchestration MCP - Tree of Thoughts with multi-agent evaluation. Fork of Anthropic's sequential-thinking with string coercion fix.
Thinkseq
An thinking and reasoning engine for the Model Context Protocol (MCP).
Server Perplexity
Enhanced MCP server with comprehensive Perplexity API parameter support for advanced development assistance
Zerodb Sequential Thinking
Persistent sequential thinking MCP — chain-of-thought reasoning that survives sessions, resumes across agents, and saves conclusions as plan artifacts. Powered by ZeroDB. Zero-con…
Cognitive Tools
Revolutionary Single-Tool-Call MCP server with Enhanced 6-Stage Cognitive Deliberation Framework combining Scientific Investigation, OOReD, and Critical Thinking methodologies wit…
Think MCP Tool
An MCP server that provides a 'think' tool for structured reasoning, based on Anthropic's engineering research
Deepthinking
Comprehensive MCP server with 34 reasoning modes (30 accessible via 13 focused tools) including historical reasoning, academic research (synthesis, argumentation, critique, analys…
Kette
Kette — Florentin One KI-Wertschöpfungskette. Die einheitliche MCP-Server-Infrastruktur für die lückenlose KI-Wertschöpfungskette nach BMFTR-HTAD-Richtlinie. Alle sieben Reasoning…
Reflective Agent Architecture
Metacognitive AI architecture combining Modern Hopfield Networks with entropy-based confusion detection for insight-like problem solving. Implements energy-based search, adaptive…
Devils Advocate
MCP server that stress-tests reasoning - devil's advocate, premortem analysis, assumption audits and steelmanning as enforced, structured protocols
Rahul Chaube Skills
The most comprehensive open-source AI skills library for LLMs, AI agents, prompt engineering, deep research, and production AI systems.
We Need Ds
Claude Code plugin that unlocks full-power We need reasoning chains in DeepSeek Pro models: turn-aware DSH minimal simulation (official one-line persona + Bash/Edit pair on decisi…
SportMind
The Sports Intelligence Library For AI Agents
Cerebro
The open-source memory engine behind Cerebro. Persistent memory, learning and reasoning for Claude Code and any MCP client. Local-first.
Cognitive Bridge
An MCP server that gives AI a compositional mind — persistent memory that catches contradictions, built on USD LIVRPS composition semantics and mechanically verified against them.
Cognitive Coalition
Claude Code-first reasoning skill: budgeted role debate, private ledger, scenario playbooks, and prompt CLI for sharper plans with less token waste.
Agent
Local-first Cognitive Execution Platform for Multi-LLM Orchestration, Autonomous Workflows, Persistent Memory & Offline Learning
GEN AI
Generative AI course notebooks: how LLMs work, prompting, RAG, agents, MCP and reasoning models.
Agentgate
Policy, human approval, and a tamper-evident audit trail for AI agent tool calls
Policy Reasoning Bench
Hand-built benchmark of regulatory and cost-benefit analysis tasks with expert rubrics — philosophy, economics, law/policy.
rikarazome/prolog-reasoner
only accuracy on 30 logic problems.
hubinoretros/deep-thinker
thinker`
Self Inspect MCP
Keyless heuristic self-inspection tool: an agent describes a thought or task and always gets back one metathought. Deterministic routing over an open CSV (no LLM). REST + MCP.
Forgewisp Core
Forgewisp — safe, function-calling AI agents for the browser. Register your own functions as validated tools, with risk-tier execution, OpenAI-compatible streaming, dual reasoning…
Warranted
Make AI research agents accountable — give every conclusion a traceable argument graph. MCP server + Claude Code plugin for paper reproduction, hypothesis verification, and audita…
Terminals Skills
Seven convergence verbs for Claude Code, OpenCode, and any MCP client: turn a messy idea-pile into a coherent answer with a checkable receipt, then act on it and keep it true. Off…
Aiaic Mcptool
aiaic_mcptool :factory_worker::toolbox::classical_building: : Agent Tools & MCP # Model Context Protocol # Interoperability # Best Practice # Integration
Deepseek Harness Acp
Standalone Agent Client Protocol (ACP) server for DeepSeek Harness with real-time streaming, reasoning trace, MCP tools, and session recovery.
ThoughtMcp
🧠 AI cognitive architecture over MCP — human-like five-sector memory, parallel reasoning, metacognition (bias/emotion/confidence), a 3D memory graph, and a web UI. PostgreSQL + pg…
Lingnao
灵脑 LingNao — 可审计·确定性·不幻觉的推理引擎（非概率生成式 LLM）。本地 A* 可审计推理 + 世界图 + 七段审计 + do 演算因果；免费 LLM 仅做感知/解释，不进入证明链。46 个 MCP 工具。授权：商业授权 / 非商业免费（非商用免费，商用须书面授权）。
Chreia
Local-first reasoning graph for investigations. Tauri desktop app + optional MCP
Kb Reasoning Agent
Technology demonstration PoC of an AI agent using LLM-based reasoning to perform complex tasks: generate an execution plan from external inputs and a knowledge base, collect relev…
AI Agent V2
A sophisticated AI agent framework with interleaved thinking, persistent memory, and MCP integration.
Loom Go
Where your AI assistant helps you think things through.
Think And Ship
An MCP server for planning, execution and validation: Structured reasoning (think_*) + execution tracking (ship_*) + roadmap + signals for AI coding agents. Rust · stdio + Streama…
Decision Lab
MCP server for structured decision-making - weighted decision matrices, criteria scoring, sensitivity analysis and a defensible recommendation
Claude Sequential Thinking MCP
Make Claude think step by step before answering - MCP server for complex reasoning, no API key needed