# iTechSmart UAIO (npm · @itechsmart/mcp-server)

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

- Trust score: 67/100 (medium)
- Change this week: +22
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.itechsmart.dev`: 25/100, [markdown](https://verifymcp.io/servers/iteksmart-mcp-server/mcp.md), [page](https://verifymcp.io/servers/iteksmart-mcp-server/mcp)
- npm · `@itechsmart/mcp-server`: 67/100 (this document), [markdown](https://verifymcp.io/servers/iteksmart-mcp-server/itechsmart-mcp-server.md), [page](https://verifymcp.io/servers/iteksmart-mcp-server/itechsmart-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `@itechsmart/mcp-server`
- Version: `2.0.3`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 86/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 26 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 5384 tokens (~81/item across 66 items; 66 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 92/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 77% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add iteksmart-mcp-server -- npx -y @itechsmart/mcp-server
```

### Codex

```bash
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
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add iteksmart-mcp-server --command npx --arg -y --arg @itechsmart/mcp-server
```

### Hermes

```yaml
mcp_servers:
  iteksmart-mcp-server:
    command: "npx"
    args: ["-y", "@itechsmart/mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "iteksmart-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@itechsmart/mcp-server"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 67, +62)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] Licence: MIT

### 2026-08-01 (score 5, −22)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-31 (score 27, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-30 (score 45, +21)

- [functional improvement] Tool coverage: unverified → 100

### 2026-07-28 (score 24, −21)

- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 45)

First indexed and scored.

## MCP tools (66)

### `verify_prooflink_receipt` (~132 tokens)

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.

Input parameters:

- `receipt_id` (string, required): The receipt ID to verify (16 hex characters)

### `get_receipt_chain` (~109 tokens)

Fetch and verify the complete ProofLink receipt chain from iTechSmart's production ledger. Returns all receipts in chronological order with full chain verification — confirming no tampering at any position.

Requires scope: ledger:audit:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input parameters:

- `container` (string): Optional: filter receipts by container name
- `limit` (number): Number of receipts to fetch (default: 20, max: 100)

### `prooflink.verify_chain` (~114 tokens)

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.

Input parameters:

- `container` (string): Optional: filter receipts by container name
- `limit` (number): Number of receipts to fetch (default: 20, max: 100)

### `prooflink.verify_receipt` (~81 tokens)

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.

Input parameters:

- `receipt_id` (string, required): The receipt ID to verify (16 hex characters)

### `prooflink.search_receipts` (~104 tokens)

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.

Input parameters:

- `container` (string): Optional: filter receipts by container name
- `limit` (number): Number of receipts to return (default: 20, max: 100)

### `mission.list_incidents` (~100 tokens)

Read-only mission scope: list recent autonomous IT incidents for audit and operations review. Alias for list_recent_incidents.

Requires scope: mission.list_incidents. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input parameters:

- `limit` (number): Number of incidents to return (default: 10, max: 50)
- `since` (string): ISO 8601 datetime — only return incidents after this timestamp

### `mission.cluster_health` (~55 tokens)

Read-only mission scope: return live cluster health without granting execution or remediation rights. Alias for cluster_status.

Requires scope: mission.cluster_health. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

### `compliance.audit_summary` (~60 tokens)

Read-only compliance scope: return the live compliance audit summary for CISO/auditor review. Alias for get_compliance_status.

Requires scope: compliance.audit_summary. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

### `query_uaio_status` (~96 tokens)

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.

### `get_incident_details` (~88 tokens)

Fetch details of a specific autonomous remediation incident including the ProofLink receipt, remediation actions taken, before/after system state, time to detect, time to remediate, and NIST control mappings.

Requires scope: incident:classify:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input parameters:

- `incident_id` (string, required): The incident ID

### `list_recent_incidents` (~125 tokens)

List recent autonomous IT remediation incidents from the iTechSmart UAIO platform. Returns chronological list with incident ID, timestamp, trigger type, autonomous action taken, detection/remediation timing, human input status, and ProofLink receipt ID.

Requires scope: incident:classify:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input parameters:

- `limit` (number): Number of incidents to return (default: 10, max: 50)
- `since` (string): ISO 8601 datetime — only return incidents after this timestamp

### `simulate_infrastructure_attack` (~134 tokens)

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.

Input parameters:

- `attack_type` (string): Type of simulated failure (default: oomkilled)

### `invoke_octoai_pipeline` (~174 tokens)

Invoke the OctoAI 7-node cognitive pipeline with a free-form prompt. Routes the question through the multi-agent reasoning chain (Knowledge Miner, Logic Engine, Systems Architect, Strategic Thinker, Physics Engine) and returns a synthesized final_answer with a confidence score. Use for open-ended platform questions, decision support, or anything that needs OctoAI's reasoning rather than a deterministic infrastructure lookup. POSTs to http://localhost:8100/query.

Requires scope: octoai:pipeline:invoke. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input parameters:

- `prompt` (string, required): The question or instruction to send to the pipeline (1-32000 chars).
- `session_id` (string): Optional session id for memory continuity (default: hermes-mcp-default).

### `get_platform_briefing` (~112 tokens)

Get a full real-time platform health briefing for the iTechSmart UAIO platform. Returns status of all 18 services (systemd + Docker), SIE finding queue counts by severity and detector, disk usage, uptime, receipts total, gate status, and next scheduled SIE scan. Use this for an instant one-shot snapshot of everything running on the platform.

Requires scope: infrastructure:briefing:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

### `get_sie_queue` (~192 tokens)

Retrieve the current SIE (Self-Improving Engine) security finding queue. Returns all pending findings with severity, detector type (gitignore_gaps, file_perms, secrets_in_repo, monoliths, in_source_token), fix class (safe_auto, needs_approval, flag_only), affected file paths, and recommended remediation action. Use to inspect what security issues SIE has flagged for human approval.

Requires scope: sie:queue:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input parameters:

- `detector` (string): Filter by detector name (e.g. "secrets_in_repo", "file_perms")
- `fix_class` (string): Filter by fix class: safe_auto | needs_approval | flag_only
- `severity_max` (number): Only return findings at or above this severity (1=critical, 5=low)

### `get_compliance_status` (~109 tokens)

Get live compliance scores for the iTechSmart platform. Returns NIST CSF (96/100), HIPAA (100/100), and SOC 2 Type II scores with per-control evidence status, gap analysis, and the source tracker file used for computation. No auth required on the upstream endpoint — data is computed live from soc2-tracker.json.

Requires scope: compliance:scores:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

### `dispatch_ag2_incident` (~179 tokens)

Dispatch an IT incident to the iTechSmart AG2 6-agent GroupChat for autonomous diagnosis. Routes through IncidentDetector -> DigitalTwinAnalyst -> RemediationPlanner -> SecurityGatekeeper -> ExecutionAgent -> ProofLinkNotary. Returns the multi-agent remediation plan and receipt ID. SEMI_AUTO mode: plan is returned for human review; execution is gated by the SecurityGatekeeper. Use for real incidents: service crashes, OOMKills, cert expiry, disk pressure, config drift.

Requires scope: ag2:incident:invoke. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input parameters:

- `description` (string, required): Incident description (what is failing and how)
- `service` (string, required): Affected service or container name
- `severity` (string): Incident severity level (default: medium)

### `search_platform_logs` (~164 tokens)

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.

Input parameters:

- `lines` (number): Number of recent log lines to return (default: 100, max: 500)
- `pattern` (string): Optional grep pattern to filter lines (e.g. "ERROR", "timeout", "started")
- `service` (string, required): systemd service name (e.g. "itechsmart-api", "djuane-ai", "iself")

### `approve_sie_finding` (~142 tokens)

Approve a specific SIE (Self-Improving Engine) security finding by queue index. Applies the associated fixer (gitignore_add, chmod_tighten, or secrets_gitignore), seals a ProofLink receipt for the fix, and removes the item from the queue. Get the index from get_sie_queue first. EXECUTE CLASS: this modifies files on disk and seals an immutable receipt.

Requires scope: sie:queue:write. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input parameters:

- `index` (number, required): Queue index of the finding to approve (use get_sie_queue to list available indices)

### `trigger_sie_scan` (~167 tokens)

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.

Input parameters:

- `mode` (string): Scan mode: dry-run (detect only) or apply (fix safe items). Default: dry-run.
- `use_llm` (boolean): Whether to use Nemotron for finding ranking and analysis. Default: true.

### `get_iself_journal` (~127 tokens)

Retrieve the iSELF (Self-Healing Loop Framework) healing history. Returns journal entries showing what service failed, what iSELF diagnosed, what patch was applied (e.g. systemctl restart), whether it succeeded, and the confidence score. iSELF runs every 5 min and has healed 11+ incidents.

Requires scope: iself:journal:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input parameters:

- `limit` (number): Number of most-recent entries to return (default: 20, max: 100)

### `integration_status` (~77 tokens)

Parallel health check across all wired integrations: Langfuse, RAGflow, Shuffle, Tactical RMM, MeshCentral, and Probo compliance. Returns ok:true/false and service-specific metadata for each.

Requires scope: integrations:status:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

### `langfuse_health` (~55 tokens)

Check Langfuse LLM observability platform health. Returns ok status and org name.

Requires scope: integrations:observe:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

### `langfuse_trace` (~143 tokens)

Create a Langfuse trace to log an LLM interaction (input, output, model, metadata).

Requires scope: integrations:observe:write. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input parameters:

- `input`: Input payload (any JSON value)
- `metadata`: Arbitrary metadata object
- `model` (string): Model ID used (e.g. claude-sonnet-4-6)
- `name` (string, required): Trace name / operation label
- `output`: Output payload (any JSON value)
- `tags` (array): Trace tags
- `userId` (string): End-user identifier

### `ragflow_health` (~52 tokens)

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.

### `ragflow_query` (~84 tokens)

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.

Input parameters:

- `dataset_ids` (array): Optional dataset filter
- `question` (string, required): Natural-language question (max 2000 chars)

### `shuffle_health` (~52 tokens)

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.

### `shuffle_trigger` (~74 tokens)

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.

Input parameters:

- `body`: Optional JSON body passed to the workflow trigger
- `workflow_id` (string, required): Shuffle workflow UUID

### `trmm_health` (~51 tokens)

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.

### `trmm_agents` (~57 tokens)

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.

### `trmm_summary` (~57 tokens)

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.

### `trmm_run_script` (~83 tokens)

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.

Input parameters:

- `agent_id` (string, required): TRMM agent ID or hostname
- `script_id` (number, required): TRMM script ID (integer)

### `mesh_health` (~55 tokens)

Check MeshCentral remote device management health. Returns ok status, admin user, and enrolled device count.

Requires scope: integrations:mesh:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

### `mesh_devices` (~53 tokens)

List all devices enrolled in MeshCentral with hostname, OS, connectivity, and group info.

Requires scope: integrations:mesh:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

### `probo_health` (~51 tokens)

Check Probo compliance platform health. Returns ok status and control count.

Requires scope: integrations:probo:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

### `probo_controls` (~58 tokens)

List all Probo compliance controls with status, category, and description (SOC2/EU AI Act).

Requires scope: integrations:probo:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

### `probo_risks` (~51 tokens)

List all Probo compliance risks with severity level and status.

Requires scope: integrations:probo:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

### `probo_summary` (~63 tokens)

Get Probo compliance aggregate summary: control pass/fail, risk high/medium/low, and task open/done counts.

Requires scope: integrations:probo:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

### `get_learning_queue` (~58 tokens)

Get patterns pending human approval from Learning Arbiter (Tier 2 items, score 50-85).

Requires scope: learning:arbiter:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

### `approve_learning_item` (~69 tokens)

Approve a Tier 2 learning pattern for promotion to Agent Brain. Requires pattern_id.

Requires scope: learning:arbiter:write. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input parameters:

- `pattern_id` (string, required): Pattern ID from get_learning_queue

### `get_learning_metrics` (~53 tokens)

Get Learning Arbiter cycle metrics: processed, promoted, rejected, known patterns.

Requires scope: learning:arbiter:read. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

### `ghl_create_contact` (~94 tokens)

Create a contact in GoHighLevel CRM. Seals a ProofLink receipt.

Requires scope: ghl:contacts:write. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input parameters:

- `company` (string, required)
- `email` (string, required)
- `first` (string, required)
- `last` (string, required)
- `phone` (string, required)
- `tags` (array)

### `ghl_trigger_workflow` (~70 tokens)

Trigger a GHL workflow for a contact. Seals a ProofLink receipt.

Requires scope: ghl:workflows:invoke. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input parameters:

- `contact_id` (string, required)
- `workflow_id` (string, required)

### `ghl_book_appointment` (~86 tokens)

Book a calendar appointment for a GHL contact. Seals a ProofLink receipt.

Requires scope: ghl:appointments:write. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input parameters:

- `calendar_id` (string, required)
- `contact_id` (string, required)
- `end_time` (string)
- `start_time` (string, required)

### `ghl_send_email` (~96 tokens)

Send email to GHL contact via Judge gate (held if flagged). Seals a ProofLink receipt.

Requires scope: ghl:messaging:write. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input parameters:

- `body` (string, required)
- `contact_id` (string, required)
- `from_email` (string)
- `from_name` (string)
- `subject` (string, required)

### `ghl_update_contact` (~64 tokens)

Update GHL contact fields. Seals a ProofLink receipt.

Requires scope: ghl:contacts:write. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input parameters:

- `contact_id` (string, required)
- `fields` (object, required)

### `ghl_move_pipeline` (~71 tokens)

Move a GHL opportunity to a new pipeline stage. Seals a ProofLink receipt.

Requires scope: ghl:opportunities:write. Every call governed by Arbiter constitutional policy and sealed with a ProofLink cryptographic receipt.

Input parameters:

- `opportunity_id` (string, required)
- `stage_id` (string, required)

### `deepgram_tts` (~97 tokens)

Convert text to speech via Deepgram Aura (aura-asteria-en). Saves MP3 to mission-videos/ and seals a ProofLink receipt. Returns mp3_url.

Input parameters:

- `output_filename` (string): Optional output filename (auto-generated if omitted)
- `text` (string, required): Text to convert (max 4000 chars)
- `voice` (string): Deepgram voice model (default: aura-asteria-en)

### `deepgram_transcribe` (~72 tokens)

Transcribe audio from URL or file path using Deepgram Nova-2. Returns transcript, confidence, and word-level timestamps. Seals a ProofLink receipt.

Input parameters:

- `audio_file_path` (string): Server-side path to audio file
- `audio_url` (string): URL of audio file to transcribe

### `deepgram_blog_audio` (~73 tokens)

Generate MP3 audio version of a blog post via Deepgram TTS. Saves to blog-audio/ directory. Returns mp3_url and filename. Seals a ProofLink receipt.

Input parameters:

- `content` (string, required): Blog post content (markdown OK, stripped automatically)
- `title` (string, required): Blog post title

### `itsm_create_ticket` (~86 tokens)

Create an ITSM ticket for an incident. Assigns priority based on severity. Returns ticket ID.

Input parameters:

- `description` (string, required): Full incident description
- `service` (string, required): Affected service name
- `severity` (string, required): Incident severity
- `source` (string): Detection source (iSELF, Prometheus, etc.)
- `title` (string, required): Incident title

### `itsm_get_ticket` (~45 tokens)

Retrieve a single ITSM ticket by ID, including embedded ProofLink receipt if sealed.

Input parameters:

- `ticket_id` (string, required): Ticket ID (e.g. ITS-10001)

### `itsm_list_tickets` (~64 tokens)

List ITSM tickets. Optionally filter by status (open/resolved) or severity.

Input parameters:

- `limit` (number): Max tickets to return (default 20)
- `severity` (string): Filter by severity
- `status` (string): Filter by status

### `itsm_close_ticket` (~49 tokens)

Close and resolve an ITSM ticket with a resolution note. Triggers ProofLink seal.

Input parameters:

- `resolution` (string, required): Resolution description
- `ticket_id` (string, required): Ticket ID to close

### `itsm_run_loop` (~71 tokens)

Trigger the full 6-step ITSM ProofLink loop: DETECT -> TICKET -> DIAGNOSE -> REMEDIATE -> VERIFY -> CLOSE+SEAL. Returns sealed ticket IDs and receipt hashes.

Input parameters:

- `dry_run` (boolean): If true, detect and ticket but do not restart services

### `itsm_run_test` (~37 tokens)

Inject a synthetic test incident through the full ITSM ProofLink loop. Returns ticket ID, receipt hash, and the embedded receipt block.

### `itsm_get_mttr_stats` (~47 tokens)

Get Mean Time To Remediate (MTTR) statistics from resolved ITSM tickets.

Input parameters:

- `last_n` (number): Analyze last N resolved tickets (default 10)

### `itsm_embed_receipt` (~71 tokens)

Embed a ProofLink SHA-256 receipt directly inside an existing ITSM ticket body.

Input parameters:

- `receipt_hash` (string, required): SHA-256 hash of the ProofLink receipt
- `receipt_id` (string): ProofLink receipt ID
- `ticket_id` (string, required): Ticket ID to embed receipt into

### `itsm_verify_receipt` (~45 tokens)

Verify the ProofLink receipt embedded in an ITSM ticket. Returns hash, chain position, and verification URL.

Input parameters:

- `ticket_id` (string, required): Ticket ID to verify

### `itsm_list_open_incidents` (~29 tokens)

List all currently open incidents (ITSM tickets with status=open), sorted by severity.

### `itsm_get_incident_timeline` (~47 tokens)

Get the full lifecycle timeline of an incident: detected, ticketed, diagnosed, remediated, verified, sealed.

Input parameters:

- `ticket_id` (string, required): Ticket ID

### `itsm_trigger_detection` (~42 tokens)

Run all 5 incident detectors (iSELF, Prometheus, Wazuh, NetworkScanner, OctoAI) and return raw findings without creating tickets.

### `itsm_get_detection_sources` (~28 tokens)

Return status and last-scan results for all 5 ITSM incident detection sources.

### `itsm_get_remediation_history` (~55 tokens)

Get the history of all auto-remediation actions, with MTTR and success rate.

Input parameters:

- `limit` (number): Max results (default 20)
- `service` (string): Filter by service name (optional)

### `itsm_register_webhook` (~48 tokens)

Register a webhook URL to receive real-time ITSM ticket state changes (OPENED, UPDATED, RESOLVED).

Input parameters:

- `url` (string, required): Webhook URL to POST events to

### `itsm_dashboard_summary` (~37 tokens)

Get the ITSM dashboard summary: open count, resolved today, avg MTTR, top failing services, and ProofLink sealing rate.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/iteksmart-mcp-server/itechsmart-mcp-server#diagnostics

## Score history

- 2026-08-03: 67
- 2026-08-02: 67
- 2026-08-01: 5
- 2026-07-31: 27
- 2026-07-30: 45
- 2026-07-28: 24
- 2026-07-27: 45

## Links

- npm package: https://www.npmjs.com/package/@itechsmart/mcp-server
- Socket report: https://socket.dev/npm/package/@itechsmart/mcp-server
- Repository: https://github.com/Iteksmart/mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/iteksmart-mcp-server/itechsmart-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/iteksmart-mcp-server/itechsmart-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/iteksmart-mcp-server/itechsmart-mcp-server