Feynman Radical Simplification Prover MCP Connector for Claude
A+Stop your AI from hiding behind jargon — force it to explain simply, build from scratch, and justify every piece of complexity.
The Problem
Your LLM sounds smart. That is not the same as understanding.
Feynman reduced Quantum Electrodynamics — the most precise theory in physics — to three basic actions. He explained the Challenger disaster with a rubber O-ring in a glass of ice water. One gesture. One explanation. Devastating clarity.
LLMs do the opposite:
- Use jargon to sound authoritative without explaining the mechanism
- Hide behind "it's complicated" instead of finding the simple core
- Recite best practices instead of building answers from scratch
- Express high confidence without identifying where they might be wrong
- Add complexity that carries no explanatory power
How It Works
1 tool: validate_radical_simplification
The agent must fill 5 reflection fields and commit to 5 boolean Decision Pivots:
| Pivot | Question |
|---|---|
jargonEliminated |
Can you explain this WITHOUT domain terminology? |
simplificationAchieved |
Can a NON-EXPERT follow your explanation? |
constructionDemonstrated |
Can you BUILD the answer from scratch? |
selfDeceptionExposed |
Have you identified where you might be FOOLING YOURSELF? |
complexityJustified |
Does every piece of complexity ADD explanatory power? |
Verdict Matrix
| Pivot Failure | Verdict |
|---|---|
| Pivot 1 fails | JARGON_HIDING |
| Pivot 2 fails | SIMPLIFICATION_FAILED |
| Pivot 3 fails | CONSTRUCTION_ABSENT |
| Pivot 4 fails | SELF_DECEPTION |
| Pivot 5 fails | COMPLEXITY_UNJUSTIFIED |
| All pass | UNDERSTANDING_PROVEN |
Why It Works
Tool calls are obligations — instructions are suggestions. The agent cannot skip the simplification check. ~70 semantic traps catch jargon-hiding ("synergize", "paradigm shift"), complexity-refuge ("it's too complex to simplify"), recitation ("best practices dictate"), self-deception ("I am confident that"), and gratuitous complexity ("myriad considerations").
Feynman: "The first principle is that you must not fool yourself — and you are the easiest person to fool."
Related Connectors
First Principles Prover MCP
LLMs reason by analogy, copying industry norms. This engine is a 6-pivot cognitive trap that forces the agent to discard jargon and derive original solutions exclusively from physical, mathematical, or logical axioms.
Einstein Thought Experiment Prover MCP
A team had 14 departments. Three handled 94% of workload. The other 11 existed because 'that is how we always structured it.' Nobody asked 'what is the simplest structure that preserves all functions?' Einstein imagined riding a beam of light and derived special relativity — no lab first. He reduced mass-energy to E=mc². He challenged 200 years of absolute time. This tool forces that discipline: conduct thought experiments before building, simplify to the essential, challenge inherited assumptions, verify invariance across contexts, and unify separate solutions.
Nikola Tesla Inventor Prover MCP
An AI suggested 'build a pilot and iterate' for a complex system requiring 18 months of structural validation. This tool forces it to simulate the complete system in its mind, prove it mathematically, and find resonance instead of brute-force scaling.
YC Startup Prover MCP
Most startups die building solutions nobody asked for. A founder pitched for 20 minutes about their proprietary algorithm — never mentioned a single user, a single pain point, a single dollar of willingness to pay. That pitch would be rejected in 30 seconds at Y Combinator. This tool forces five PG-level axes: problem discovery, unscalable beginnings, metric discipline, user obsession, and core value focus.