Skip to content

Sophon Consulting

by sophon.consulting · remote · no sign-in to list tools · v1.0.0 · published by consulting.sophon

Read-only, deterministic AI triage and readiness tools implementing Sophon's published rubrics.

Changes · 2
CompareRegistry entry

2 tools: 2 change things.

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 sophon-consulting https://www.sophon.consulting/api/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 2Claude Code: ask
  • assess_ai_readinessAssess an organization's readiness to run AI in production across five dimensions (data readiness, workflow ownership, governance and controls, delivery capacity, executive sponsor…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
    Assess an organization's readiness to run AI in production across five dimensions (data readiness, workflow ownership, governance and controls, delivery capacity, executive sponsorship), each scored 1-5 with evidence or marked unknown, plus classified candidate use cases. Returns a deterministic verdict — Ready, Ready with conditions, Not yet ready, or Insufficient evidence (thresholds: ready needs no dimension below 3; 2+ dimensions at 2 or below is not yet ready) — with a handoff-ready Markdown assessment. Read-only; not for triaging a single AI idea (use triage_ai_opportunity).

    Annotations the server declares

    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false
  • triage_ai_opportunityScore one proposed AI workflow across bottleneck severity, value capture, integration readiness, and risk posture.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
    Score one proposed AI workflow across bottleneck severity, value capture, integration readiness, and risk posture. Returns a deterministic go-deeper or hold recommendation and a handoff-ready Markdown artifact. Read-only; not for organization-wide readiness reviews or production rollout planning.

    Annotations the server declares

    • readOnlyHint: true
    • 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 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http sophon-consulting https://www.sophon.consulting/api/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": [],
    "ask": [
      "mcp__sophon-consulting__triage_ai_opportunity",
      "mcp__sophon-consulting__assess_ai_readiness"
    ],
    "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 sophon-consulting. Review it before you use it.