ThoughtProof

io.github.ThoughtProofPublished by GitHub account ThoughtProofv0.3.2Updated Nov 10, 2026

Pre-action gate: verify before pay/trade/write/deploy. execute=true only on ALLOW.

The publisher's own server: Proof Holdings

VerifiedSTDIODesktop onlyFinanceSecurity & MonitoringAI & ML

Overview

AI-generated overview

Local stdio MCP server that lets an AI agent verify a proposed action before paying, trading, writing or deploying, returning a fail-closed execute flag.

What you can do
  • Verify a proposed action before execution: submit mandate, proposed action and reasoning to get a verdict, objections and receipt, with routing to spend or irreversible-exit checks
  • Verify claims and AI-generated reasoning at a chosen stake level, domain and depth
  • Look up an agent's composite trust score on the ERC-8004 registry
  • Run an optional pre-execution gate for trading agents
  • Return a fixed envelope where execute is true only on ALLOW
When to use it
Use it when an agent is about to take a consequential step — spend money, check out, publish, delete, deploy or write memory — and you want an independent check before it acts. Also useful for fact-checking claims or reasoning, or looking up agent trust scores.
Requirements
Node.js 18+ and a local stdio MCP client such as Claude Desktop, Cursor, Windsurf or Cline; run via npx. A DQL_API_KEY is needed for the default verify_decision path; SENTINEL_API_KEY is needed when mode=sentinel or auto-route picks Sentinel; THOUGHTPROOF_API_KEY is an operator key for verify_claim, verify_trade and Sentinel fallback. Keys are obtained from the provider's pricing page, and network access to the provider API is required.
Before you install
Requires paid provider API keys (DQL_API_KEY, SENTINEL_API_KEY, THOUGHTPROOF_API_KEY) that must be kept out of source control. The mandate, proposed action, reasoning and context you submit are sent to the provider's API. Fail-closed behavior is soft: the tool returns execute=false but does not hard-stop the host, so the client must honor it. A missing Sentinel key returns execute=false rather than falling back to DQL.

Installation

In SourceWeft

  1. Open ThoughtProof in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

thoughtproof-mcp

[npm version] [CI] [HOL Guard Scanner] [HOL Verified] [License: MIT]

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

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

json
{  "mcpServers": {    "thoughtproof": {      "command": "npx",      "args": ["-y", "[email protected]"],      "env": {        "DQL_API_KEY": "<YOUR_DQL_VERIFY_KEY>"      }    }  }}

Install with npx -y [email protected]. Works with Claude Desktop, Cursor, Windsurf, Cline, and other local stdio MCP clients.

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.

ParameterTypeDefaultDescription
mandatestring(required)User's stated goal / instruction
proposed_actionstring(required)What the agent is about to do
reasoningstring(required)The agent's own plan / reasoning
contextstring(optional)Extra evidence
modedql / sentinel / autoautoExplicit surface, or auto-route

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):

json
{  "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.

ParameterTypeDefaultDescription
claimstring(required)The text to verify
stakeLevellow / medium / high / criticalmediumRisk level — higher stakes trigger deeper verification
domainfinancial / medical / legal / code / generalgeneralDomain context for specialized verification
speedfast / standard / deepstandardVerification depth

check_agent_score

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

ParameterTypeDescription
agentIdstringAgent ID to look up
domainstringOptional domain filter

verify_trade

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

Configuration

Environment VariableDefaultDescription
DQL_API_KEY(none)DQL key (dqlk_…) for the default verify_decision path. Alias: THOUGHTPROOF_DQL_KEY
SENTINEL_API_KEY(none)Optional. Required only when mode=sentinel or auto-route picks Sentinel. Fallback: THOUGHTPROOF_API_KEY as X-Sentinel-Key
DQL_SANDBOX(off)Set to 1 to send sandbox: true on DQL calls (local/dev only)
THOUGHTPROOF_API_KEY(none)Operator key for verify_claim / verify_trade / Sentinel fallback
THOUGHTPROOF_BASE_URLhttps://api.thoughtproof.aiRV API base URL (verify_claim)

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

Development

bash
git clone https://github.com/ThoughtProof/thoughtproof-mcp.gitcd thoughtproof-mcpnpm installnpm run buildnpm testnpm 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.

Security

See SECURITY.md for supported versions, private reporting ([email protected]), and key handling (dqlk_… for MCP hero — never commit real keys).

HOL listing / Guard scanner score is a review baseline only. It is not next-action authorization and not a substitute for fail-closed host behavior (execute: true only on ALLOW).

Related

  • ThoughtProof — Decision verification for AI agents
  • pot-cli — CLI for reasoning verification
  • ERC-8004 — Autonomous Agent Registry

License

MIT — ThoughtProof

Source: README.md at commit cb7a6c6

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.3.2LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Proof integrations