DXPert UNS Tools — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Follow-up value is specific to Keyless Sparkplug B topic linting and industrial-readiness diagnostics: Do free topic conventions remain versioned separately from private industrial-data access?

Reviewed Oct 5, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

Free local UNS/Sparkplug B linting and industrial AI-readiness screening.

What we know

Zero-key stdio MCP with offline Sparkplug B topic linting and UNS naming checks plus a public industrial AI-readiness diagnostic.

Maintenance / activity evidence

@dxpert/uns-tools 0.1.3 published 2026-10-05T02:18:41.551Z

Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Read/analysis only.
Authentication not yet verified.
Sensitive access: Industrial namespace/topic metadata, Diagnostic answers

Low authority; avoid treating readiness output as an operational safety certification.

Full authority, access and evidence limits are available in Review context and Access & risk.

All limitations / Review context

Do free topic conventions remain versioned separately from private industrial-data access?

The bounded review of the publisher's documented Keyless Sparkplug B topic linting and industrial-readiness diagnostics and release notices identified no disclosed material condition preventing an accurately scoped public tracking entry. The resource's operational permissions remain uncertainty; this assessment does not certify installation safety.

Low authority; avoid treating readiness output as an operational safety certification.
Read/analysis only.
Topic/naming validation is local; readiness diagnostic sends submitted diagnostic inputs to dxpert.ai.
Sensitive access: Industrial namespace/topic metadata, Diagnostic answers
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited.
Documented tool authority and any remote data handling must be checked before installation or use.
Tool inventory, client matrix and permissions completeness were not requirements for this Radar tracking review.
Readiness diagnostic is preliminary self-reported screening, not an audit.
One diagnostic tool calls dxpert.ai; local validators are offline.
No write/control action is exposed.

Original activity observations

@dxpert/uns-tools 0.1.3 published 2026-10-05T02:18:41.551Z

Technical identity

npm/@dxpert/uns-tools

Exact implementation source: https://www.npmjs.com/package/@dxpert/uns-tools ↗
Reviewed resource type: MCP Server
Repository identity: dxpert-ai/uns-tools
Package identity: npm:@dxpert/uns-tools

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 5, 2026 · Latest source observation Oct 8, 2026

Package registry ↗
@dxpert/uns-tools
Recorded package identity, distribution or download evidence.
Includes references whose attribution is not established.
GitHub repository ↗
dxpert-ai/uns-tools
Repository reference; implementation attribution is not established for every document.
Includes references whose attribution is not established.

Setup · Watchlist

Install & Agents

Publisher instructions.

Source evidence observed Oct 14, 2026.

Additional setup details required — see the specific gaps below.

Install / connect
Publisher instructions
Offline validators lint_sparkplug_topic and check_uns_namespace; run_readiness_diagnostic makes an unauthenticated network request.
publisher install or stdio launch · Claude Code only · Publisher instructions
claude mcp add dxpert-uns-tools -- npx -y @dxpert/uns-tools
Configure / authenticate
MCP100 setup guide
Publisher `claude mcp add dxpert-uns-tools -- npx -y @dxpert/uns-tools`; no key required.
Check connection
Suggested check
Use `check_uns_namespace` on a synthetic topic, which runs locally/offline.
Remove / uninstall / revoke
MCP100 setup guide
For a Claude Code registration named `dxpert-uns-tools`, run `claude mcp remove dxpert-uns-tools`; otherwise remove the exact entry in the chosen MCP client settings and restart/reconnect. This client-host removal command is MCP100-composed from Claude Code lifecycle documentation, not a vendor-authored uninstall. With `npx`, a separate global package uninstall normally is unnecessary. Do not delete provider data or credentials by default.
Client unregister, package uninstall, data deletion, and OAuth/API token/wallet permissions are distinct.
Remove client registration · Claude Code only · MCP100 composed guide
claude mcp remove dxpert-uns-tools

Official Documentation & Sources

What it does

Zero-key stdio MCP with offline Sparkplug B topic linting and UNS naming checks plus a public industrial AI-readiness diagnostic.

Capability: Security & Testing
Resource type: MCP Server
Industry: Manufacturing & Industrial
Best fit: Free local UNS/Sparkplug B linting and industrial AI-readiness screening.

Representative uses

Lint Sparkplug B topics
Check UNS naming conventions/collisions
Run AI-readiness diagnostic

Limitations

Readiness diagnostic is preliminary self-reported screening, not an audit.
One diagnostic tool calls dxpert.ai; local validators are offline.
No write/control action is exposed.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Not documented in the reviewed sources
Permissions: Read/analysis only.
Data handling: Topic/naming validation is local; readiness diagnostic sends submitted diagnostic inputs to dxpert.ai.
Cost: free
Risk and cautions: Low authority; avoid treating readiness output as an operational safety certification.

Access scope and cautions

Write actions: None in the reviewed inventory
Sensitive access: Industrial namespace/topic metadata Diagnostic answers
Risk level: low

FAQ

Based on reviewed evidence as of 2026-10-08. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: Lint Sparkplug B topics; Check UNS naming conventions/collisions; Run AI-readiness diagnostic.

What setup and authentication are documented?

Recorded installation/entrypoint step: npx -y @dxpert/uns-tools. Recorded transport: stdio. Recorded environment-variable notes: DXPERT_API_BASE (optional). No configuration values are supplied here. Prerequisites: Node.js 18+. These are the documented setup details, not a claim that installation or client compatibility was independently tested. Authentication: No key/account required.

Can it modify data or perform write operations?

The reviewed inventory lists no write actions. An empty inventory alone does not establish read-only authority. Recorded permission boundary: Read/analysis only.

What data-handling boundary should I consider?

Topic/naming validation is local; readiness diagnostic sends submitted diagnostic inputs to dxpert.ai. Recorded sensitive-access context: Industrial namespace/topic metadata; Diagnostic answers.

What limitations and risks should I check before use?

Low authority; avoid treating readiness output as an operational safety certification. Readiness diagnostic is preliminary self-reported screening, not an audit. One diagnostic tool calls dxpert.ai; local validators are offline. No write/control action is exposed. Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited. Documented tool authority and any remote data handling must be checked before installation or use.