Smart-Thinking
About
An advanced MCP server for multi-dimensional, adaptive, and collaborative reasoning.
Details
- Author
- leghis
- Categories
- Other, AI, Knowledge Base
- Tags
- #research
Jump to
Setup
Install Smart-Thinking in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/leghis/Smart-Thinking
Follow the installation instructions in the repository README, then restart your MCP client.
Smart-Thinking is a Model Context Protocol (MCP) server that delivers graph-based, multi-step reasoning without relying on external AI APIs. Everything happens locally: similarity search, heuristic-based scoring, verification tracking, memory, and visualization all run in a deterministic pipeline designed for transparency and reproducibility.
- Graph-first reasoning that connects thoughts with rich relationships (supports, contradicts, refines, contextual links, and more).
- Local TF-IDF + cosine similarity engine powering memory lookups and graph expansion without third-party embedding services.
- Heuristic quality evaluation that scores confidence, relevance, and quality using transparent rules instead of LLM calls.
- Verification workflow with detailed statuses and calculation tracing to surface facts, guardrails, and uncertainties.
- Persistent sessions that can be resumed across runs, keeping both the reasoning graph and verification ledger in sync.
- Session bootstrap–ReasoningOrchestratorinitializes a session, restores any saved graph state, and prepares feature flags.
- Pre-verification– deterministic guards inspect the incoming thought, perform light-weight calculation checks, and annotate the payload.
- Graph integration– the thought is inserted intoThoughtGraph, linking to context, prior thoughts, and relevant memories.
- Heuristic evaluation–QualityEvaluatorandMetricsCalculatorcompute weighted scores and traces that explain the decision path.
- Verification feedback– statuses fromVerificationServiceand heuristic traces are attached to the node and propagated across connections.
- Persistence & response– updates are written toMemoryManager/VerificationMemory, and a structured MCP response is returned with a timeline of reasoning steps.
Each step is logged with structured metadata so you can visualize the reasoning fabric, audit decisions, and replay sessions deterministically.
Smart-Thinking ships as an npm package compatible with Windows, macOS, and Linux.
git clone https://github.com/Leghis/Smart-Thinking.git cd Smart-Thinking npm install npm run build npm link
Need platform-specific configuration details? SeeGUIDE_INSTALLATION.mdfor step-by-step instructions covering Windows, macOS, Linux, and Claude Desktop integration.
- smart-thinking-mcp— start the MCP server (globally installed package).
- npx -y smart-thinking-mcp— launch without a global install.
- npm run start— execute the built server from source.
- npm run demo:session— run the built-in CLI walkthrough that feeds sample thoughts through the reasoning pipeline and prints the resulting timeline.
The demo script showcases how the orchestrator adds nodes, evaluates heuristics, and records verification feedback step by step.
Smart-Thinking is validated across the most popular MCP clients and operating systems. Use the new connector mode (--mode=connectororSMART_THINKING_MODE=connector) when a client only accepts thesearchandfetchtools required by ChatGPT connectors.1
Need a minimal deployment footprint? Combine--transport=http --mode=connectorwith a reverse proxy (ngrok, fly.io, render, etc.) so remote clients can consume the server without exposing the full toolset.
For registry scanners and fallback metadata extraction, Smart-Thinking also exposes:
- feature-flags.tstoggles advanced behaviours such as external integrations (disabled by default) and verbose tracing.
- config.tsaligns platform-specific paths and verification thresholds.
- memory-manager.tsandverification-memory.tsstore session graphs, metrics, and calculation results using deterministic JSON snapshots.
- Smart-Thinking runs fully in local deterministic mode without any API key.
- External verification/search connectors are disabled by default inToolIntegrator.
- To explicitly enable external connectors, set:
export SMART_THINKING_ENABLE_EXTERNAL_TOOLS=true
- If external connectors are disabled (default), verification suggestions stay local (executePython,executeJavaScript) and external tool calls return a local fallback result.
- FeatureFlags.externalLlmEnabledandFeatureFlags.externalEmbeddingEnabledremain disabled by default, so no remote LLM/embedding provider is required.
npm run build # Compile TypeScript sources npm run lint # ESLint across src/ npm run test # Jest test suite npm run test:coverage # Jest coverage report npm run watch # Incremental TypeScript compilation
Seedocs/modernisation-smart-thinking-v12-plan.mdfor the modernization checklist and rollout tracking.
- Deterministic heuristics and verification eliminate dependency on remote LLMs.
- Latest validation (February 6, 2026):80.47%statements,81.59%lines,84.34%functions,63.48%branches.
- CI recommendations: runnpm run lintandnpm run test:coveragebefore each release candidate.
Contributions are welcome. Please open an issue or pull request describing the change, and run the quality checks above before submitting.
-
OpenAI, “Building MCP servers for ChatGPT and API integrations,” highlights that connectors requiresearchandfetchtools for remote use. (https://platform.openai.com/docs/mcp)↩↩2
OpenAI Agents SDK documentation on MCP transports (stdio, SSE, streamable HTTP). (https://openai.github.io/openai-agents-python/mcp/)↩
Model Context Protocol client catalogue listing Claude, Cline, Kilo Code, and other MCP-compatible applications. (https://modelcontextprotocol.io/clients)↩↩2↩3
Cursor documentation for configuring MCP servers via stdio/SSE/HTTP transports. (https://cursor.com/docs/context/mcp)↩
OpenEnded Philosophy MCP Server with NARS Integration
A philosophical reasoning system combining OpenEnded Philosophy with the Non-Axiomatic Reasoning System (NARS) for advanced analysis and synthesis.
MCP server for the Oyemi semantic lexicon. Provides deterministic word-to-code mapping and valence/sentiment analysis for AI agents like Claude, ChatGPT, and Gemini.
AI Reasoning Cache & Consensus Layer with 50+ reasoning objects across 14 domains. Cache hit/miss with token savings, failure risk check before execution, cross-model verification, and citation tracking. 11 MCP tools via Streamable HTTP.
Advanced cognitive thinking MCP server with DAG-based thought graph, multiple reasoning strategies, metacognition, and self-evaluation.
Mnemex is a Python MCP server that provides AI assistants with human-like memory dynamics through temporal decay and natural spaced repetition, storing memories locally in human-readable JSONL and Markdown formats.
Generate academic papers with verified citations via AI
A tool for structured, step-by-step ethical reasoning using multiple moral frameworks for transparent deliberation.
next-generation MCP reasoning tool. successor to Waldzell AI's Clear Thought.
Cited compliance, legal & security intelligence for AI agents — 300+ law, regulation and standards corpora (GDPR, NIS2, AI Act, DORA) with article-level citations, plus live CVE/KEV/EPSS vulnerability context. OAuth remote server, free tier
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
