{
  "mcpServers": {
    "thoughtproof": {
      "command": "npx",
      "args": ["-y", "thoughtproof-mcp"],
      "env": {
        "THOUGHTPROOF_API_KEY": "tp_op_your_key_here"
      }
    }
  }
}

⚠️ UNCERTAIN (42% confidence)

Claim: "GPT-5 achieves 95% accuracy on MMLU-Pro"

Objections:
- Insufficient public benchmark data to confirm
- Historical accuracy claims have been overstated
- MMLU-Pro methodology has known ceiling effects

⚡ 3.2s | Adversarial Multi-Model Consensus

Your AI Agent
    │
    ▼
┌──────────────────┐
│  thoughtproof-mcp │  ← MCP Server (this package)
└──────────────────┘
    │
    ▼
┌──────────────────┐
│  ThoughtProof API │  ← api.thoughtproof.ai (RV)
└──────────────────┘
    │
    ▼
┌───────────────────────────────────────────┐
│  Stage 1: Independent Evaluation       │
│  3–4 LLMs (Grok, Gemini, DeepSeek,     │
│  Sonnet) each examine the claim         │
│                                         │
│  Stage 2: Red-Team Critique             │
│  1 dedicated model challenges all       │
│  initial verdicts                        │
│                                         │
│  Stage 3: Synthesis                     │
│  Sonnet weighs verdicts + critique      │
│  → final decision                       │
└───────────────────────────────────────────┘
    │
    ▼
  ALLOW / BLOCK / UNCERTAIN
  + confidence % + objections

git clone https://github.com/ThoughtProof/thoughtproof-mcp.git
cd thoughtproof-mcp
npm install
npm run build
npm test
npm run dev          # Run with tsx (hot reload)
npm run inspect      # Test with MCP Inspector