automateyournetwork/netclaw/claroty-asset-inventory
Claude Code and agent skill by automateyournetwork/netclaw
- community
Checking that the SKILL.md file is still in the repository.
Discover and classify OT / IoT / IoMT assets via Claroty xDome. List devices by site, Purdue level, and device purpose; assign Purdue layers and custom attributes; cross-reference with Nautobot / NetBox SoT to surface drift.
Install
npx vskill@latest install automateyournetwork/netclaw/claroty-asset-inventorySKILL.md
The same SKILL.md was published earlier as automateyournetwork/netclaw/claroty-asset-inventory.
Claroty Asset Inventory
OT / IoT / IoMT asset discovery, Purdue Model classification, and source-of-truth reconciliation, using the Claroty xDome MCP server.
When to Use
- Building an OT asset inventory for a site, plant, or facility
- Filtering devices by Purdue level (0 — process; 1 — control; 2 — supervisory; 3 — operations; 3.5 — DMZ; 4/5 — enterprise)
- Identifying devices by purpose (PLC, HMI, RTU, engineering workstation, historian, IP camera, medical device)
- Assigning a Purdue layer to a newly discovered device (ITSM-gated write)
- Recording an out-of-band classification or compliance tag via custom attributes (ITSM-gated write)
- Cross-referencing xDome's discovered inventory against Nautobot or NetBox source-of-truth and surfacing drift
MCP Server
- Server:
claroty-mcp(in-repo,mcp-servers/claroty-mcp/claroty_mcp_server.py) - Command:
python3 -u mcp-servers/claroty-mcp/claroty_mcp_server.py(stdio transport) - Auth: Bearer token via
CLAROTY_API_TOKEN - ITSM: Write operations require a ServiceNow CR (
CHG\d+); bypassed inNETCLAW_LAB_MODE=true
Available Tools
| Tool | Parameters | What It Does | |
|---|---|---|---|
list_devices | site_id?, purdue_level?, device_purpose?, name_contains?, limit?, offset?, max_items? | List xDome-managed devices with rich filters | |
get_device_details | device_id | Full record for a single device including raw attributes | |
set_device_purdue_level | device_id, purdue_level, cr_number | Write (ITSM-gated) — assign Purdue layer | |
set_device_custom_attribute | device_id, attribute_key, attribute_value, cr_number | Write (ITSM-gated) — set a custom attribute |
For cross-referencing, also reach for:
nautobot_get_ip_address/nautobot_get_prefixfrom the nautobot-sot skillnetbox-reconcilefrom the NetBox skills
Workflow Examples
Inventory by site and Purdue layer
Calls list_devices(site_id="warehouse-east", purdue_level="Level 1", limit=50). Returns a GCF-encoded device table.
Find every PLC in the fleet
Calls list_devices(device_purpose="PLC", max_items=500).
Classify a newly discovered device
Calls set_device_purdue_level(device_id="7a2c...", purdue_level="Level 2", cr_number="CHG0012345"). The ITSM gate validates the CR before the POST.
SoT drift check
list_devices(site_id="warehouse-east")→ xDome setnautobot_get_ip_address(...)filtered by site → SoT set- The agent diffs MAC / IP / name and reports IP_DRIFT, MISSING_FROM_SOT, and MISSING_FROM_XDOME entries.
Tag for compliance audit
Calls set_device_custom_attribute(device_id="9f4d...", attribute_key="compliance_scope", attribute_value="PCI", cr_number="CHG0012999").
ITSM gating
All write tools call validate_change_request(cr_number) from mcp-servers/claroty-mcp/utils/itsm_gate.py. The CR must:
- Match
CHG\d+. - Be in "Implement" state in ServiceNow (skipped in
NETCLAW_LAB_MODE=true).
A rejection returns {"itsm_gate": {...}, "applied": false} and the xDome call is NOT made.
Token scope expectations
If set_device_purdue_level or set_device_custom_attribute returns applied: false and an error object with status_code: 403, the ITSM gate passed and the request body is correct — xDome rejected at RBAC. The token in CLAROTY_API_TOKEN lacks write scope on devices. Don't retry — escalate to whoever provisions xDome API tokens.
GAIT audit
Every tool invocation is recorded in GAIT. The audit trail includes the tool name, parameters, CR number (for writes), and the xDome response status.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingworkspace/skills/claroty-asset-inventory/SKILL.md
Popularity
- Repository stars
- 674
- Repository forks
- 189
- 7-day trend score
- 33
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/automateyournetwork/netclaw/claroty-asset-inventory)