thoughtproof-mcp

thoughtproof-mcp — local stdio. Hero tool verify_decision (DQL spend / Sentinel irreversible exit). execute is true only on ALLOW.

MCP server for ThoughtProof — pre-execution decision verification for AI agents.

Hero tool: verify_decision. It routes inside the tool to DQL (spend / checkout) or Sentinel (irreversible exit) and returns a fail-closed execute flag. execute is true only on a native ALLOW.

This package is a local stdio MCP server (Node 18+) for Desktop / CLI hosts such as Cursor, Claude Desktop, Windsurf, and Cline. It is not a remote HTTP MCP server. It is not a Grok Web/Mobile custom connector.

Get keys at https://app.thoughtproof.ai/pricing.

Unpublished work is documented in UNRELEASED.md.

Quick Start

{
  "mcpServers": {
    "thoughtproof": {
      "command": "npx",
      "args": ["-y", "thoughtproof-mcp@0.3.2"],
      "env": {
        "DQL_API_KEY": "dqlk_your_key_here"
      }
    }
  }
}

Install with npx -y thoughtproof-mcp@0.3.2. Works with Claude Desktop, Cursor, Windsurf, Cline, and other local stdio MCP clients.

Related MCP server: agentshield-mcp

Tools

verify_before_action / verify_decision (hero)

verify_before_action is an alias of verify_decision (identical schema + handler). Soft fail-closed: host must honor execute=false.

Pre-execution gate for a proposed action. Routing is inside the tool — not an agent quiz.

Auto-route: spend / checkout / booking / purchase / payment / cart / Stripe / price / budget / cap → DQL. High-blast irreversible exit without that language (publish, delete, deploy, send-to-prod, memory write) → Sentinel. Unsure → DQL. Explicit mode wins. RV / PLV are not on this path.

Camera mandate: do not put the overshoot in proposed_action or reasoning (for example, do not write “price is above the cap”). The verifier has to find the mismatch.

Envelope (always this shape):

{
  "verdict": "ALLOW",
  "execute": true,
  "objections": [],
  "receipt_id": "dql_…",
  "surface": "dql",
  "axes": [],
  "recommendation": "execute"
}

execute is true only on ALLOW. REVIEW, UNCERTAIN, BLOCK, timeouts, HTTP 402/4xx/5xx, and missing keys return execute: false. Fail-closed is soft at the protocol layer — the tool does not hard-stop the host. Replan is a new call (new receipt).

verify_claim

Verify any claim or AI-generated reasoning via RV (POST /v1/check). Unchanged.

check_agent_score

Look up an agent's composite trust score on the ERC-8004 registry.

verify_trade

Optional pre-execution gate for trading agents (Sentinel → RV). Not the default verify_decision path. See VERIFY_TRADE.md.

Configuration

A missing Sentinel key returns execute: false with “Sentinel key not configured” — it does not silently call DQL.

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

For local MCP clients, point command at node and args at dist/index.js after npm run build.

Related

• ThoughtProof — Decision verification for AI agents

• pot-cli — CLI for reasoning verification

• ERC-8004 — Autonomous Agent Registry

License

MIT — ThoughtProof