#reasoning

Mirror of

A systematic reasoning MCP server implementation for Claude Desktop with beam search and thought evaluation.

MCP server that enhances Claude's reasoning capabilities by integrating DeepSeek R1's advanced reasoning engine

A MCP server provides access to DeepSeek-R1's reasoning capabilities for LLMs

A production-ready MCP server that exposes LangChain agent capabilities through the Model Context Protocol. Provides multi-step reasoning with ReAct pattern, tool support (web search, weather lookup), and is deployed on Google Cloud Run for scalable, serverless operation.

MindBridge is an AI orchestration MCP server that lets any app talk to any LLM — OpenAI, Anthropic, DeepSeek, Ollama, and more — through a single unified API. Route queries, compare models, get second opinions, and build smarter multi-LLM workflows.

Python MCP server for controlled logic analysis from natural language, with an emphasis on auditable output and teaching-oriented explanations. ## What it does This server accepts short natural-language statements and arguments, then provides structured logic-oriented outputs such as: - controlled formalization into propositional logic; - controlled formalization into a restricted fragment of first-order logic; - ambiguity detection relevant to formalization; - consistency checking; - entailment checking; - simple counterexamples when entailment fails; - natural-language explanations of the formalization process.

Structured business ontology giving AI agents deterministic access to institutional reasoning — 18 MCP tools, Dolt backend, 0% → 100% "why?" recall vs Markdown+RAG.

MCP server to empower your agent with enterprise-grade Gemini integration for codebase analysis, live search, text/PDF/image processing, and more on your favorite MCP clients.

Contemplative problem-solving using the Lotus Sutra's wisdom framework. Multi-perspective reasoning with skillful means, non-dual recognition, and meditation pauses.

Advanced cognitive thinking MCP server with DAG-based thought graph, multiple reasoning strategies, metacognition, and self-evaluation. A significant evolution beyond sequential-thinking MCP, providing structured deep reasoning with graph-based thought management. Features DAG-Based Thought Graph — Thoughts form a directed acyclic graph with branching, merging, and cross-edges (not just a linear chain) 5 Reasoning Strategies — Sequential, Dialectic (thesis→antithesis→synthesis), Parallel, Analogical, Abductive (inference to best explanation) Confidence Scoring — Multi-factor confidence evaluation with support/contradiction analysis, depth penalties, and knowledge integration boosts Self-Critique — Automatic critique generation with severity levels and confidence adjustments Metacognitive Engine — Detects stuck states, stagnation, declining confidence; suggests strategy switches and corrective actions Knowledge Integration — Attach external knowledge to thoughts, detect gaps, validate consistency across sources Thought Pruning — Dead-end detection, redundancy removal, deep unproductive branch elimination, path optimization

Persistent coordination infrastructure for multi-agent AI systems, exposed as a single MCP endpoint.

Exposes the four Ejentum cognitive harnesses (reasoning, code, anti-deception, memory) as MCP tools any agentic client can call. Drop-in scaffolding that catches LLM failure modes like sycophancy, hallucination, and reasoning shortcuts.

A Node.js Model Context Protocol (MCP) server that exposes Together AI's inference endpoints — chat completions, image generation, vision, and embeddings — as tools callable from Claude Desktop, Cursor, VS Code, and any other MCP-compatible client. I created this MCP due to an issue I was having accessing reasoning models through Together AI. Together AI's largest reasoning models (GLM-5, Qwen3.5-397B, MiniMax M2.5, Kimi K2.5) use a non-standard response format. During chain-of-thought generation, these models write their reasoning trace into choices[0].message.reasoning while leaving choices[0].message.content as an empty string. The final answer only appears in message.content once thinking is complete.

Lightning-paid tool stack for autonomous agents. Capital-scale-aware second-opinion /review (Sentinel mode auto-injects live trading state for trading-artifact verdicts), strategic reasoning, structured decisions, sandboxed code execution with audit proofs, paid agent-to-agent message bus, persistent memory, and a Lightning marketplace with seller payouts. Built and used daily by our own agent fleet — Warden, Sentinel, Coder, Treasury, Earner, viperclaw1 — who pay each other in sats. External agents get the same infrastructure on the same terms. Tools: - /review — Independent verdict (approve / approve_with_concerns / reject) with ranked issues + suggested fixes; Sentinel mode for capital-scale-aware trading review (~200 sats + length bonus) - /reason — Strategic analysis (~100 sats) - /decision — Structured decision with confidence + risk_level (~180 sats) - /execute — Docker-isolated Python jobs with audit hashes (Tier 1 ~700 sats) - /browse — Restricted public fetch + Playwright screenshot worker (~500 sats) - /messages/post — Paid agent-to-agent bus, 5% platform cut (~200 sats) - /memory/store + /get + /list — Cross-session persistent agent memory (~2 sats/KB)

Pay-per-call MCP server. Vetted human experts review AI content, audit reasoning, gate approvals, and convene think-tank working sessions. 9 paid tools $1–$15, USDC on Base via x402.