base120-mcp
base120-mcp
120 validierte mentale Modelle, gebündelt als MCP-Server, um Reasoning, Prompt Engineering und Architekturentscheidungen in Claude Desktop, Cursor und Windsurf zu verbessern.
Schnellstart • Die 6 Domänen • Claude Desktop Einrichtung • Engineering-Verifikation
Die 6 Reasoning-Domänen
Related MCP server: Tycana
Was ist Base120?
Die meisten KI-Agenten tun sich mit komplexen, mehrdeutigen Problemen schwer, weil sie standardmäßig aus einer einzigen Perspektive schlussfolgern.
Base120 ist eine strukturierte Bibliothek von 120 operativen mentalen Modellen (Inversion, First Principles, Ashby's Law of Requisite Variety, Nash Equilibrium, Antifragility), die LLMs die genauen Operatoren liefern, um schwierige technische Herausforderungen zu dekonstruieren.
Claude Desktop Einrichtung
Füge base120-mcp direkt zu deiner claude_desktop_config.json hinzu:
{
"mcpServers": {
"base120": {
"command": "python",
"args": ["-m", "base120_mcp.server"]
}
}
}Jetzt kannst du Claude in natürlicher Sprache fragen:
"Nutze Base120 Inversion und Ashby's Law, um unsere neue Architektur für verteilte Aufgabenwarteschlangen kritisch zu bewerten."
Bereitgestellte MCP-Tools
base120_search: Durchsuche mentale Modelle nach Domäne oder Problembeschreibung.base120_apply: Erzeuge strukturierte Reasoning-Gerüste, um ein bestimmtes Modell auf eine aktive Problemstellung anzuwenden.
Engineering-Rigor & Verifikation
Tests: 100 % bestandene Testsuite unter Python 3.10-3.13.
Null Abhängigkeiten: Reine Python-Standardbibliothek (
json,sys,dataclasses).Autor: Reuben Bowlby — LinkedIn | Lebenslauf
Enterprise-Kern
Base120 ist der kognitive Reasoning-Kern der HUMMBL-Plattform. Für Enterprise-Multi-Agent-Governance und formale Lean-4-Verifikation besuche github.com/hummbl-io.
This server cannot be deployed
Maintenance
Related MCP Connectors
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
Patterns for designing and reviewing AI skills, agents, and multi-agent workflows. Find guidance on context economy, delegation, verification, and tool design; inspect claims, worked examples, maturity labels, and source references. Five read-only tools let agents discover relevant patterns, compare concise cards, read specific sections, and explore relationships. Hosted Streamable HTTP at https://agentic-atlas.dev/mcp/ — no installation, account, or API key required. Browse the atlas at https://agentic-atlas.dev/.
Your product team's shared strategic memory — an MCP server your AI tools reason over.
Hosted MCP memory: save sessions/decisions once, search from Claude, Cursor, ChatGPT. EU-hosted FTS.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA production-ready reasoning engine that integrates Claude AI with specialized MCP tools for knowledge retrieval, schema validation, and domain-specific rubric evaluation. It enables structured RAG-based analysis across legal, health, and science domains via a RESTful API.-
- AlicenseNot gradedqualityDmaintenanceAI-native productivity backend that gives your AI assistant persistent memory, pattern awareness, and computed intelligence about your work. 14 MCP tools for task management, daily planning, weekly review, and personal context.MIT
- AlicenseAqualityCmaintenancePersistent cloud memory for AI coding assistants. 28 MCP tools for semantic search, auto-learning, task tracking, correction patterns, knowledge graphs, and session replay across Claude Code, Cursor, Windsurf, Cline, and any MCP client. Encrypted at rest. Team shared memory with author attribution.35992 npm7MIT
- AlicenseAqualityBmaintenanceCognitive prosthetic for AI agents. Indexes conversation history from ChatGPT, Claude Code, Cursor, and Gemini CLI into searchable embeddings. 25 MCP tools including tunnel_state (resume where you left off), switching_cost (quantify context-switch penalty), thinking_trajectory (track idea evolution), and alignment_check (decisions vs principles). LanceDB + Parquet, 12ms recall, local-first.25179 PyPI81MIT