Security ๐งช Community โ Claude Code โ Claude Desktop Standalone โข SentinelOne
SentinelOne
SentinelOne XDR - threat detection, incident response, and endpoint agent management via the Purple AI MCP server
Installation
Install this plugin individually:
/plugin marketplace add wyre-technology/msp-claude-plugins --plugin sentinelone Or install all MSP plugins at once:
/plugin marketplace add wyre-technology/msp-claude-plugins Features
- Alert Handling
- Asset Inventory
- Cloud Security Posture
- Purple AI Threat Hunting
- PowerQuery Analytics
- Vulnerability Management
Skills
This plugin provides 7 skills that teach Claude about SentinelOne:
| Skill | Description |
|---|---|
alerts | SentinelOne's read-only unified alert surface: the list/search/get alert tools plus notes and history, severity levels, status values, view types, GraphQL filter syntax, and cursor-based pagination. |
inventory | SentinelOne's unified asset inventory across four surface types โ agent-managed endpoints, AWS/Azure/GCP cloud resources, AD/Entra identities, and Ranger-discovered network devices. |
misconfigurations | Cloud security posture findings from SentinelOne's XSPM module across AWS, Azure, GCP, Kubernetes, identity providers, and infrastructure-as-code. |
purple-ai | The `purple_ai` tool โ SentinelOne's natural language investigation assistant over the full Singularity telemetry model. |
threat-hunting | PowerQuery against the Singularity Data Lake: the Scalyr-based pipeline syntax (distinct from SPL, SQL, KQL, and Elasticsearch DSL), the powerquery, get_timestamp_range, and iso_to_unix_timestamp tools, time-range and row-limit handling, common hunting scenarios, and the Purple AI generation path. |
vulnerabilities | CVE tracking through SentinelOne's XSPM module: the read-only vulnerability tools, EPSS scores and exploit-maturity values and why they outrank raw CVSS severity for prioritization, status values and their transitions, the vulnerability field reference, and patch-prioritization and reporting workflows. |
api-patterns | The SentinelOne Purple MCP server and the APIs behind it: uvx installation and transport modes, Service User token levels, the 23 read-only tools organized by domain, and the dual GraphQL (cursor pagination) / REST (offset pagination) architecture with its differing filter syntaxes, rate limits, and error causes. |
Agents
This plugin provides 2 agents for autonomous task execution:
| Agent | Description |
|---|---|
endpoint-hardening-auditor | Use this agent when an MSP needs to audit and harden SentinelOne endpoint configuration across client sites โ not to investigate active threats, but to proactively identify gaps before attackers can exploit them. |
threat-hunter | Use this agent when an MSP needs to autonomously hunt for threats across client endpoints using SentinelOne. |
Commands
Available slash commands:
| Command | Description |
|---|---|
/alert-triage | Triage new and unresolved SentinelOne alerts by severity |
/asset-inventory | Asset inventory summary by surface type across managed environments |
/hunt-threat | Threat hunting via Purple AI and PowerQuery execution |
/investigate-alert | Deep investigation of a specific SentinelOne alert with timeline and context |
/posture-review | Cloud security posture review with compliance gap analysis |
/vuln-report | Generate a vulnerability summary report with severity breakdown and top CVEs |
API Reference
| Base URL | |
| Authentication | |
| Rate Limit | |
| Documentation |
Example Usage
Triage new and unresolved SentinelOne alerts by severity
/alert-triage Asset inventory summary by surface type across managed environments
/asset-inventory Threat hunting via Purple AI and PowerQuery execution
/hunt-threat Deep investigation of a specific SentinelOne alert with timeline and context
/investigate-alert Cloud security posture review with compliance gap analysis
/posture-review Generate a vulnerability summary report with severity breakdown and top CVEs
/vuln-report Using Skills
/skill sentinelone:alerts
SentinelOne's read-only unified alert surface: the list/search/get alert tools plus notes and history, severity levels, status values, view types, GraphQL filter syntax, and cursor-based pagination.