Skip to content
MCP server

dxpert.ai — free UNS tools (no API key)

Lint Sparkplug B topics and check UNS naming offline, with no key or account

Runs locallyStatus and history
Install
Pricing
Free
Platforms
CLI
Runs
Locally
Version
0.1.4
Listing updated
3 days ago

About dxpert.ai — free UNS tools (no API key)

dxpert.ai — free UNS tools (no API key) is a free MCP server for developer tools. It runs locally on your machine and is started by your AI client.

Unified Namespace projects tend to rot through small naming slips, and this server catches them with two offline validators that run on your machine. It is the agent-friendly twin of the free tools page on dxpert.ai and, per the README, has no trial counter, sign-up or environment variables.

The Sparkplug linter checks MQTT topics against the Sparkplug 3.0 grammar: the spBv1.0 namespace, the eight message types plus STATE, node versus device level counts, the older 2.2 STATE form, publish-side wildcards, empty levels and characters that break downstream consumers. It returns ordered fail, warn, pass and info findings but never connects to a broker or decodes payloads. The namespace checker looks for inconsistent hierarchy depth, mixed casing, whitespace, sibling case collisions, duplicates and stray wildcards, and judges naming only.

A third tool runs the public readiness diagnostic. It is the only one that calls the network, sends a 16-answer intake, and returns ten axis scores from 0 to 5, a maturity stage and blocking gaps, labelled a preliminary self-reported screening. It is rate limited. Requires Node 18 or newer.

Install

Run in a terminal

claude mcp add uns-tools -- npx -y @dxpert/uns-tools

Add to claude_desktop_config.json

{
  "mcpServers": {
    "uns-tools": {
      "command": "npx",
      "args": [
        "-y",
        "@dxpert/uns-tools"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "uns-tools": {
      "command": "npx",
      "args": [
        "-y",
        "@dxpert/uns-tools"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "uns-tools": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@dxpert/uns-tools"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "uns-tools": {
      "command": "npx",
      "args": [
        "-y",
        "@dxpert/uns-tools"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "uns-tools": {
      "command": "npx",
      "args": [
        "-y",
        "@dxpert/uns-tools"
      ]
    }
  }
}

Configuration

  • DXPERT_API_BASEAPI base URL for the free readiness diagnostic. Defaults to production; override only for testing.

Tools this server provides (3)

Taken from the project documentation; the running server may differ.

lint_sparkplug_topic
Validates MQTT topic strings against the Sparkplug B topic grammar, offline.
check_uns_namespace
Checks UNS topic paths for naming and hierarchy inconsistencies, offline.
run_readiness_diagnostic
Runs the public industrial AI-readiness diagnostic over the network.

What it does

Sparkplug B linter
Validates topics against the Sparkplug 3.0 grammar.
Namespace consistency check
Flags mixed casing, uneven depth, duplicates and case collisions.
Readiness diagnostic
Scores a 16-answer intake across ten axes.
Offline validators
The two linting tools run locally with no network.
No credentials
Needs no API key, account or env block.
Structured findings
Returns fail, warn, pass and info results.

Good for

  • Check a batch of MQTT topics before deploying a Sparkplug edge node
  • Audit a UNS hierarchy for casing and depth inconsistencies
  • Catch topic wildcards accidentally used when publishing
  • Run a quick AI-readiness screening of a plant
  • Validate naming in a CI step through an agent

Pricing

Free

Free, no sign-up

Prices change. Check dxpert.ai before you buy.

dxpert.ai — free UNS tools (no API key) FAQ

Do I need an API key?

No. It needs no key, account or environment variables.

Which tools work offline?

lint_sparkplug_topic and check_uns_namespace.

Does the linter connect to my broker?

No, it only analyses topic strings.

How reliable is the diagnostic?

It is a preliminary self-reported screening, not an audit.

How do I get agents that read my own data?

That lives in the separate @dxpert/mcp server, which uses a dxp_ key.

Is dxpert.ai — free UNS tools (no API key) free?

Yes. dxpert.ai — free UNS tools (no API key) is free to use.

How do I add dxpert.ai — free UNS tools (no API key) to Claude Code?

Run this command in your terminal: claude mcp add uns-tools -- npx -y @dxpert/uns-tools

What are the best alternatives to dxpert.ai — free UNS tools (no API key)?

The closest alternatives to dxpert.ai — free UNS tools (no API key) are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to dxpert.ai — free UNS tools (no API key)

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Open-source analytics app where an AI agent builds charts and dashboards from your data

    • Remote
    • Open source
    • 7.7K GitHub stars
    • Analytics and data