Skip to content

MUJ428 Trust Layer — Bind Approved Intent to Verified Effect

by wmujahid428-web · remote · no sign-in to list tools · v1.6.4 · published by GitHub user wmujahid428-web

Payment-rail-independent intent-to-effect integrity for consequential agent actions.

Changes · 1
CompareRegistry entry

2 tools: 1 change things and 1 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http muj428-trust-layer https://agents.muj428.com/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

2 tools

Changes things 1Claude Code: ask
  • trust_actionVERIFY BEFORE ACT across payments, purchases, delegation, approvals, writes, releases, commits, and other consequential actions.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    VERIFY BEFORE ACT across payments, purchases, delegation, approvals, writes, releases, commits, and other consequential actions. Returns ALLOW, VERIFY, REQUIRE_VERIFICATION, or DENY plus Trust Receipt v1.3; FREE_PREFLIGHT execution_authority=false and no funds are moved.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 1Claude Code: allow
  • get_evidence_signal_requirementsReturns MUJ428 evidence-check payment, network, endpoint, and assurance-pricing requirements before an autonomous payment.No findings

    Why it is in this group

    • The name "get_evidence_signal_requirements" says "get": a word for reading.
    Description, as the server wrote it
    Returns MUJ428 evidence-check payment, network, endpoint, and assurance-pricing requirements before an autonomous payment.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.6.4. Values in angle brackets are yours to fill in.

claude mcp add --transport http muj428-trust-layer https://agents.muj428.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__muj428-trust-layer__get_evidence_signal_requirements"
    ],
    "ask": [
      "mcp__muj428-trust-layer__trust_action"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as muj428-trust-layer. Review it before you use it.