Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

iTechSmart UAIO

NPM · @ITECHSMART/MCP-SERVER · 2 COMPONENTS · SCANNED SEP 20

Connect AI agents to iTechSmart UAIO, ProofLink verification, and autonomous IT operations.

0 this week 81 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 31 of 95 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability76
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 5384 tokens (~81/item across 66 items; 66 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management93
  • Stability observed for 28 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage92
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 77% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "ghl_send_email" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 66 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the iTechSmart UAIO MCP server?

iTechSmart UAIO runs locally as an npm package, launched with npx -y @itechsmart/mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @itechsmart/mcp-server

# add to Claude Code
claude mcp add iteksmart-mcp-server -- npx -y @itechsmart/mcp-server
// .cursor/mcp.json
{
  "mcpServers": {
    "iteksmart-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@itechsmart/mcp-server"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "iteksmart-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@itechsmart/mcp-server"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add iteksmart-mcp-server -- npx -y @itechsmart/mcp-server
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "iteksmart-mcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@itechsmart/mcp-server"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add iteksmart-mcp-server --command npx --arg -y --arg @itechsmart/mcp-server
# ~/.hermes/config.yaml
mcp_servers:
  iteksmart-mcp-server:
    command: "npx"
    args: ["-y", "@itechsmart/mcp-server"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "iteksmart-mcp-server": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@itechsmart/mcp-server"
      ]
    }
  }
}
# add to Vellum
assistant mcp add iteksmart-mcp-server -t stdio -c npx -a -y @itechsmart/mcp-server
// mcp.json
{
  "mcpServers": {
    "iteksmart-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@itechsmart/mcp-server"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 15 Sept 26 0
    • Stability: 0.97 → pass security
  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Sept 26 −3
    • Stability: pass → 0.80 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed npm/@itechsmart/mcp-server@2.0.3

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 95 packages
Packages resolved 95
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 66 exposed · ~5,384 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
prooflink.search_receipts ~104

Read-only audit scope: search recent ProofLink receipts for ledger-backed post-hoc reconstruction. Supports the same limit/container filters as get_receipt_chain. Requires scope: prooflink.search_receipts. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

NameTypeReqDescription
containerstringOptional: filter receipts by container name
limitnumberNumber of receipts to return (default: 20, max: 100)

No output schema declared.

No examples provided.

prooflink.verify_chain ~114

Read-only audit scope: verify the ProofLink receipt chain for EU AI Act Article 12, CISO, and auditor workflows. Alias for get_receipt_chain; safe for production API keys without admin rights. Requires scope: prooflink.verify_chain. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

NameTypeReqDescription
containerstringOptional: filter receipts by container name
limitnumberNumber of receipts to fetch (default: 20, max: 100)

No output schema declared.

No examples provided.

prooflink.verify_receipt ~81

Read-only audit scope: verify one ProofLink receipt by ID without granting mutation rights. Alias for verify_prooflink_receipt. Requires scope: prooflink.verify_receipt. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

NameTypeReqDescription
receipt_idstringyesThe receipt ID to verify (16 hex characters)

No output schema declared.

No examples provided.

query_uaio_status ~96

Get the current operational status of the iTechSmart UAIO (Unified Autonomous IT Operations) platform. Returns real-time metrics including container health, ProofLink receipts generated and chain breaks, last autonomous remediation time/duration, NIST CSF and HIPAA compliance scores, and overall platform status. Requires scope: infrastructure:scan:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

ragflow_health ~52

Check RAGflow RAG platform health. Returns ok status and dataset count. Requires scope: integrations:rag:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

ragflow_query ~84

Query the RAGflow knowledge base with a natural-language question. Optionally filter to specific dataset IDs. Requires scope: integrations:rag:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

NameTypeReqDescription
dataset_idsarrayOptional dataset filter
questionstringyesNatural-language question (max 2000 chars)

No output schema declared.

No examples provided.

search_platform_logs ~164

Search live systemd journal logs for any iTechSmart service. Returns matching log lines from journalctl filtered by service name and optional keyword pattern. Use for real-time troubleshooting: find errors, trace restarts, check last N lines of any service. Requires scope: infrastructure:logs:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

NameTypeReqDescription
linesnumberNumber of recent log lines to return (default: 100, max: 500)
patternstringOptional grep pattern to filter lines (e.g. "ERROR", "timeout", "started")
servicestringyessystemd service name (e.g. "itechsmart-api", "djuane-ai", "iself")

No output schema declared.

No examples provided.

shuffle_health ~52

Check Shuffle SOAR platform health. Returns ok status, user, and workflow count. Requires scope: integrations:shuffle:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

shuffle_trigger ~74

Trigger a Shuffle SOAR workflow by workflow ID with an optional request body. Requires scope: integrations:shuffle:invoke. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

NameTypeReqDescription
bodyOptional JSON body passed to the workflow trigger
workflow_idstringyesShuffle workflow UUID

No output schema declared.

No examples provided.

simulate_infrastructure_attack ~134

Trigger a simulated infrastructure attack on the iTechSmart break-it sandbox to demonstrate the UAIO autonomous loop. Simulation: injects an OOMKilled / connection_exhausted / disk_full / crashloop event, runs detect → twin → classify → fix → prove, returns a ProofLink receipt with the 5 UAIO phases. SANDBOX ONLY — no production systems are affected. Requires scope: digitaltwin:simulate:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

NameTypeReqDescription
attack_typestringType of simulated failure (default: oomkilled)

No output schema declared.

No examples provided.

trigger_sie_scan ~167

Kick off a fresh SIE (Self-Improving Engine) scan of the iTechSmart platform. dry-run mode: detects and ranks findings without applying any fixes. apply mode: applies all safe_auto fixes and queues the rest for approval. Runs in the background — check get_platform_briefing for queue count after ~2 min. EXECUTE CLASS: apply mode modifies files and seals receipts. Requires scope: sie:scan:invoke. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

NameTypeReqDescription
modestringScan mode: dry-run (detect only) or apply (fix safe items). Default: dry-run.
use_llmbooleanWhether to use Nemotron for finding ranking and analysis. Default: true.

No output schema declared.

No examples provided.

trmm_agents ~57

List all Tactical RMM managed agents with status, OS, site, and last-seen info. Requires scope: integrations:trmm:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

trmm_health ~51

Check Tactical RMM health. Returns ok status and enrolled agent count. Requires scope: integrations:trmm:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

trmm_run_script ~83

Run a saved script on a Tactical RMM agent by agent ID and script ID. Requires scope: integrations:trmm:invoke. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

NameTypeReqDescription
agent_idstringyesTRMM agent ID or hostname
script_idnumberyesTRMM script ID (integer)

No output schema declared.

No examples provided.

trmm_summary ~57

Get Tactical RMM agent summary: total, online, offline, overdue counts, and site list. Requires scope: integrations:trmm:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

verify_prooflink_receipt ~132

Verify the cryptographic integrity of a ProofLink receipt from iTechSmart's autonomous IT operations platform. ProofLink receipts are SHA-256 hash-chained cryptographic proofs of autonomous AI actions. This tool verifies hash integrity, chain link to the previous receipt, and schema completeness. Returns: verification result with tamper_detected flag, individual check results, and human-readable summary. Requires scope: prooflink:verify:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

NameTypeReqDescription
receipt_idstringyesThe receipt ID to verify (16 hex characters)

No output schema declared.

No examples provided.

Common questions

What is the iTechSmart UAIO MCP server?

iTechSmart UAIO is an MCP server listed in the public MCP registry as io.github.Iteksmart/mcp-server. Connect AI agents to iTechSmart UAIO, ProofLink verification, and autonomous IT operations. This page covers its npm package (@itechsmart/mcp-server).

Is the iTechSmart UAIO MCP server safe to use?

iTechSmart UAIO scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the iTechSmart UAIO MCP server expose?

iTechSmart UAIO exposes 66 tools: verify_prooflink_receipt, get_receipt_chain, prooflink.verify_chain, prooflink.verify_receipt, prooflink.search_receipts, and 61 more. Their descriptions and schemas cost roughly 5,384 tokens of context every time the server is loaded.

Is the iTechSmart UAIO MCP server still maintained?

iTechSmart UAIO is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the iTechSmart UAIO MCP server under?

iTechSmart UAIO declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.