ThoughtProof MCP
ThoughtProof/thoughtproof-mcp
Verificação adversarial de claims com consenso multi-modelo LLM
Ver no GitHubServidor MCP para verificação adversarial de raciocínio em IA usando consenso multi-modelo. Claude, Grok e DeepSeek avaliam independentemente cada afirmação, retornando ALLOW, BLOCK ou UNCERTAIN com pontuação de confiança e atestação assinada via JWKS.
Instalação
npx convez-ai ThoughtProof/thoughtproof-mcp1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Validar afirmações críticas antes de tomar decisões em código ou dados
- Verificar saída de agentes IA em ambientes de alta importância (financeiro, médico, legal)
- Detectar alucinações e raciocínio falho em tempo real durante execução de tarefas
Veredito

Ferramenta sólida para governança de IA em produção. O mecanismo adversarial multi-modelo reduz alucinações e oferece rastreabilidade criptográfica, mas o custo por verificação ($0.02–$0.08) limita uso em cenários de volume altíssimo.
README
A tradução para o português deste README ainda está na fila.
thoughtproof-mcp
MCP server for ThoughtProof — verify AI reasoning with adversarial multi-model consensus.
3–4 LLMs (Grok, Gemini, DeepSeek, Sonnet) independently evaluate every claim. A dedicated red-team model critiques their verdicts. A synthesizer (Sonnet) weighs everything and returns ALLOW, BLOCK, or UNCERTAIN with confidence score and objections.
Quick Start
{
"mcpServers": {
"thoughtproof": {
"command": "npx",
"args": ["-y", "thoughtproof-mcp"],
"env": {
"THOUGHTPROOF_API_KEY": "tp_op_your_key_here"
}
}
}
}
Works with Claude Desktop, Cursor, Windsurf, Cline, and any MCP-compatible client.
Tools
verify_claim
Verify any claim or AI-generated reasoning before acting on it.
| Parameter | Type | Default | Description |
|---|---|---|---|
claim | string | (required) | The text to verify |
stakeLevel | low / medium / high / critical | medium | Risk level — higher stakes trigger deeper verification |
domain | financial / medical / legal / code / general | general | Domain context for specialized verification |
speed | fast / standard / deep | standard | Verification depth |
check_agent_score
Look up an agent's composite trust score on the ERC-8004 registry.
| Parameter | Type | Description |
|---|---|---|
agentId | string | Agent ID to look up |
domain | string | Optional domain filter |
Example
In Claude Desktop or Cursor, just ask:
"Verify the claim: GPT-5 achieves 95% accuracy on MMLU-Pro"
The tool returns:
⚠️ 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
How It Works
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
Pricing
| Speed | Models | Cost per verification |
|---|---|---|
| fast | 2 | $0.008 |
| standard | 4 | $0.02 |
| deep | 5+ | $0.08 |
Payment: API key (operator account) or x402 micropayment (USDC on Base).
API Key
Get an operator API key at thoughtproof.ai. Without a key, verifications use x402 micropayments automatically.
Configuration
| Environment Variable | Default | Description |
|---|---|---|
THOUGHTPROOF_API_KEY | (none) | Operator API key |
THOUGHTPROOF_BASE_URL | https://api.thoughtproof.ai | API base URL |
Development
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
Related
- ThoughtProof — Decision verification for AI agents
- pot-cli — CLI for reasoning verification
- ERC-8004 — Autonomous Agent Registry
License
MIT — ThoughtProof