MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
An MCP server built around Donella Meadow's book "Thinking in Systems, a primer"
★ 7 -
Enhanced Sequential Thinking MCP server with parallel and reflective thinking capabilities
npm MIT -
systems-thinkinggithub.com/davidpanter/systems-thinkingupdated this year
MCP server providing systems thinking models as composable analysis lenses. Gives Claude structured mental models for analyzing architecture, incidents, and technical decisions.
★ 1 -
Comprehensive Thinking Tools MCP - 24 cognitive frameworks + Context Engine with semantic search + Documentation Intelligence + Memory System + Multi-Language Support + Bridged Context7 Integration (works in concert with Robinson's Toolkit MCP)
npm MIT -
3. Clone your repo (skip if already done) git clone https://github.com/The-Think-Tank/healthcare-management-system.git cd healthcare-management-system # 4. Deploy MCP Server render services create web \ --name mcp-server \ --env node \ --rootDir server \ --buildCommand "npm install && tsc" \ --startCommand
-
An advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.
★ 306 -
omnimind-mcpupdated this year
OMNIMIND - Infinite Dimensional Thinking System with MCP - Cross-platform (Android/Linux/Mac/Windows)
npm MIT -
brain-mcpgithub.com/DDguan2010/brain-mcpupdated this year
AI memory thinking management system, simulating human-like thinking and memory processes
MIT ★ 3 -
@gotza02/smartagentupdated this year
SmartAgent - Intelligent Multi-Agent System with Sequential Thinking & Auto-Routing
npm MIT -
ai-brain-mcpupdated this year
Memory Control Protocol - AI memory and thinking management system
npm ISC -
digital-brain-mcpupdated this year
Memory Control Protocol - AI memory and thinking management system
npm MIT -
MLX-Powered Agentic RAG System implementing Anthropic's Code execution with MCP pattern, featuring Claude Code hooks, skills, and MLX acceleration with Qwen3-VL-2B-Thinking for enhanced reasoning
-
Experimental system dynamics modeler with a library of 1,000 example models. For serious work, use Simlin (simlin.com).
MIT ★ 1 -
Unconventional-thinkinggithub.com/stagsz/Unconventional-thinkingupdated this year
An MCP server for unconventional and boundary-breaking problem-solving through an advanced note-taking system.
MIT ★ 30 -
deep-thinkergithub.com/hubinoretros/deep-thinkerupdated this year
Advanced cognitive thinking MCP with DAG-based thought graph, 10 reasoning strategies, node aliases, session persistence, structured responses, auto strategy selection, and 17 tools with help & conclude
npm MIT -
Ariadnes-Mirror-MCPgithub.com/IsaiahN/Ariadnes-Mirror-MCPupdated this year
Ariadne is an MCP that finds solutions in fields of study you'd never think to look.
-
Free `/m:os` stock-and-flow modeling over MCP and CLI
npm MIT -
Clear Thought MCP server with modular architecture - 38 reasoning operations for systematic thinking
npm MIT -
Mapas causais interativos com narrativas apresentáveis — local-first, hospedado sem conta, com MCP, REST e CLI para agentes.
MIT -
Multi-disciplinary mental models & cognitive coaching for AI agents via NPX
npm MIT -
fpf-thinker-assistantgithub.com/nergal-perm/fpf-thinker-assistantupdated this year
A specialized subsystem designed to guide humans and AI agents through rigorous First Principles reasoning. It acts as the "Laboratory" of the system, providing the *soft constraints* (heuristics, cognitive scaffolding, prompt engineering) required to convert vague "Problems" into structured "Hypotheses" and "Decisions".
MIT -
@jun-b/supadesign-mcpgithub.com/jun-b-github/supadesign-mcpupdated this year
Design Principles Engine - Universal UI quality through principles, not heuristics
npm MIT -
linsenkasten-mcpgithub.com/mistakeknot/linsenkastenupdated this year
MCP server and CLI for 288 FLUX lenses - works with Claude, ChatGPT, Codex CLI via OpenAPI/function calling
npm MIT -
Multi-round AI expert debate system via MCP - Three thought leaders engage in deep discussions on any topic
pypi MIT ★ 7 -
Intelligent MCP Memory System with Task Manager - Domain-specific knowledge organization and autonomous task management for AI assistants
npm MIT -
Remote Apple Events for System 7, plus screenshots for context: anything can control, monitor and build on a classic Mac over a socket via MPW ToolServer — Basilisk II, SheepShaver, or real 68k hardware; TCP or serial. 30 MCP tools let any AI model drive it (frontier models already know MPW and Inside Macintosh); the bridge itself needs neither.
MIT ★ 8