Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@base120-mcp Apply First Principles and Inversion to our API caching design."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
120 validated mental models packaged as an MCP server to upgrade reasoning, prompt engineering, and architectural decisions in Claude Desktop, Cursor, and Windsurf.
Quickstart • The 6 Domains • Claude Desktop Setup • Engineering Verification
Related MCP server: Tycana
Most AI agents struggle with complex, ambiguous problems because they default to single-perspective reasoning.
Base120 is a structured library of 120 operational mental models (Inversion, First Principles, Ashby's Law of Requisite Variety, Nash Equilibrium, Antifragility) that give LLMs the exact operators needed to deconstruct hard engineering challenges.
Add base120-mcp directly to your claude_desktop_config.json:
{
"mcpServers": {
"base120": {
"command": "python",
"args": ["-m", "base120_mcp.server"]
}
}
}Now you can ask Claude in natural language:
"Use Base120 Inversion and Ashby's Law to critique our new distributed task queue architecture."
base120_search: Search mental models by domain or problem description.
base120_apply: Generate structured reasoning scaffolds for applying a specific model to an active problem statement.
Tests: 100% passing test suite across Python 3.10-3.13.
Zero Dependencies: Pure Python standard library (json, sys, dataclasses).
Author: Reuben Bowlby — LinkedIn | Resume
Base120 is the cognitive reasoning core of the HUMMBL platform. For enterprise multi-agent governance and formal Lean 4 verification, visit github.com/hummbl-io.
This server cannot be deployed
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
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.
Give your AI agent persistent, governed memory for every project. At task start it recalls the approved decisions, conventions, risks and architecture (semantic search, ranked by importance); at close it proposes what was learned as typed memories that you review and approve — governance, not a notes dump. Agents propose, humans govern: edits go back to pending and deletion is human-only by design. Connect Claude Code, Cursor, Claude Desktop or any MCP client in two minutes with just your API key — hosted (nothing to install) or locally via `uvx solucortex-mcp`. Built by SoluAI and dogfooded daily: SoluCortex is developed using its own living memory.
