Decision Integrity

io.github.wheelerhubbellPublished by GitHub account wheelerhubbellv1.0.0Updated Oct 24, 2026

Paid x402 evaluator for evidence, warrant, provenance, and represented action authority.

VerifiedStreamable HTTPWeb executableSecurity & MonitoringAI & ML

Overview

AI-generated overview

A remote paid evaluator that checks whether evidence and represented authority actually warrant a requested action or conclusion.

What you can do
Evaluate a decision: submit evidence and a requested action or conclusion and get a judgment on whether the evidence and represented authority warrant it. Detect reasoning faults: flags unsupported inference, qualifier stripping, erased unknowns, broken provenance and exceeded decision boundaries. Answer authorization questions: check whether a given action is authorized by the represented authority. Each call is billed at exactly 1 USDC.
When to use it
Use it when you want a second, independent check before acting on a conclusion drawn from evidence, or before treating an action as authorized. Useful for auditing reasoning chains where provenance and stated limits matter.
Requirements
A remote streamable HTTP endpoint; no local package or runtime is needed. No authentication, environment variables or headers are declared. Each call costs 1 USDC, so a payment-capable client is needed.
Before you install
Every call costs exactly 1 USDC, so repeated or automated use spends real money. The evidence and decision details you submit are sent to a third-party hosted service. The evaluation is advisory and does not itself grant authority or guarantee correctness.

Installation

In SourceWeft

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

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.wheelerhubbell%2Fdecision-integrity/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "decision-integrity": {
      "type": "http",
      "url": "https://decision-integrity-service.wheelerhubbell.chatgpt.site/agent/mcp"
    }
  }
}

README

This repository has no README.

Tools

1

evaluate_decision_integrity

Evaluate evidence, warrant, and authority

Evaluate whether evidence and represented authority warrant a requested action. Detect unsupported inference, qualifier stripping, erased unknowns, broken provenance, and exceeded decision boundaries. Exactly 1 USDC per call. Does this evidence warrant this conclusion? Is this action authorized? Do I have sufficient warrant to act? Are unknowns being erased? Are qualifiers being stripped? Is this inference warranted? Does provenance support this recommendation? Does the requested action exceed represented authority?

ParametersactionrequiredclaimsrequiredevidencerequiredquestionrequiredunknownsrequiredwarrantsrequiredauthorityrequiredrequestIdrequiredconditionsrequiredqualifiersrequired

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

75% 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 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.