SentinelOne MCP

SentinelOne + AI - for Claude, the ChatGPT desktop app, GitHub Copilot, Gemini CLI, and any agent that speaks MCP

Unofficial. Community-built Claude Code Skill and MCP server for the SentinelOne

API. Not affiliated with, endorsed by, or sponsored by SentinelOne, Inc..

▶ Watch the 30-second demo - demo data is simulated; every command shown exists in the real CLI.

Every SentinelOne v2.1 management endpoint, plus an offline SQLite store and cross-entity analytics - fleet health, threat triage, blast radius, drift - that no console view offers. Works with the AI you already use - ChatGPT (desktop app), Claude Desktop, Codex, Claude Code, Claude Cowork, and GitHub Copilot - plus Gemini CLI. Free, open source, runs on your laptop. Built for MSP owners. No code required.

Works with your agent

Security note. Local agents use the default stdio transport and need no

network listener. HTTP mode (--transport http, for remote agents) refuses to

start until SENTINELONE_MCP_HTTP_TOKEN is set, rejects any request without that

bearer token, serves http://127.0.0.1:7777/mcp by default, and needs --tls-cert

and --tls-key for any other address. It refuses a request body over 4 MiB or

one that takes longer than 30 seconds to arrive. Whoever holds the token can

call every tool with your SentinelOne credentials, including tools that change

your tenant, so treat it like a password, and keep SENTINELONE_MCP_READ_ONLY=1

on a remote host that only needs to read. See mcp-install.md.

The six agents MSP owners actually use (self-serve, works today):

The ChatGPT desktop app runs sentinelone-mcp locally and shares MCP configuration with Codex (OpenAI). ChatGPT on the web needs a remote server, which msp-skills does not support yet. If your team works there, a hosted gateway is the better pick; check that your AI app is on the gateway's setup list. Setup steps: mcp-install.md.

Also for the Microsoft and Google stacks

Big install base, but an honest heads-up: Gemini CLI runs the local binary you just installed, while Microsoft 365 Copilot and the Gemini app need a remote server, which msp-skills does not support yet.

Skill-native agents (also covered): Hermes and OpenClaw read this skill's SKILL.md directly *and* speak MCP - see their install sections below. Also works with Cursor, Windsurf, Cline, Continue.dev, and Zed via MCP. Full per-tool wire-up: [docs/which-agent.md](../../docs/which-agent.md).

Run more than one agent? Install across all 51+ supported agents in one command: npx skills add Servosity/msp-skills@latest (requires Node.js, then run the per-skill installer for the CLI/MCP binaries). See docs/which-agent.md.

Install in 60 seconds

Fastest for Claude Desktop - one-click .mcpb

Claude Desktop bundle: the .mcpb launches on macOS (Intel and Apple Silicon), Windows x64 and Linux x64. Every tool shells out to the companion sentinelone-cli. Releases cut from 2026-09-18 on ship that CLI inside the bundle; older bundles contain only the MCP server, so if yours lacks the companion, run the Path A or Path B installer below first (or set SENTINELONE_CLI_PATH to an existing binary). Details: #331.

Download SentinelOne MCP (.mcpb) - then open Claude Desktop > Settings > Extensions and select the file. One click, no JSON, no shell. (Browse every SentinelOne release on the releases page.)

Prefer the Claude Code plugin? Add the marketplace once, then install - works immediately, no directory listing required:

/plugin marketplace add Servosity/msp-skills

/plugin install sentinelone@msp-skills

Path A - paste one prompt into your AI agent (recommended)

Copy this into Claude Code, Codex CLI, or Claude Cowork:

Install the SentinelOne Skill and MCP server from Servosity/msp-skills in this agent workspace. If this workspace uses a POSIX shell (macOS, Linux, WSL, or Bash), run bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/sentinelone/install.sh). If it uses Windows PowerShell, run iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/sentinelone/install.ps1 | iex. Then authenticate per the README and run sentinelone-cli --help to explore.

The same prompt works in any agent that can run shell.

Path B - run the installer yourself

Windows (PowerShell):

iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/sentinelone/install.ps1 | iex

macOS / Linux:

bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/sentinelone/install.sh)

The installer drops both sentinelone-cli (the CLI) and sentinelone-mcp (the MCP server) into your user bin path. Claude Code, Codex, and Cowork discover the Skill via SKILL.md in this directory.

Verify:

sentinelone-cli --version

Upgrade to the latest version

The installer always fetches the current release - re-run it to upgrade:

macOS / Linux:

bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/sentinelone/install.sh)

Windows (PowerShell):

iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/sentinelone/install.ps1 | iex

Claude Desktop .mcpb users: download the latest .mcpb (top of this section) and re-select it in Settings > Extensions. Claude Code plugin users: /plugin update sentinelone@msp-skills.

Add to Claude Desktop, the ChatGPT desktop app, GitHub Copilot, Gemini CLI, or another MCP client

After the installer runs, see [mcp-install.md](./mcp-install.md) and [docs/which-agent.md](../../docs/which-agent.md) for the per-agent wire-up - one section per agent, including the GitHub Copilot servers key and the ChatGPT desktop app. Claude Desktop's Settings > Extensions panel is the simplest path; the MCP config block (for users who prefer editing JSON) is documented in mcp-install.md.

Install for Hermes

From the Hermes CLI:

hermes skills install servosity/msp-skills/skills/sentinelone --force

Inside a Hermes chat session:

/skills install servosity/msp-skills/skills/sentinelone --force

Hermes speaks MCP natively, so it can also use the sentinelone-mcp server directly - same install path, same env vars.

Install for OpenClaw

Tell your OpenClaw agent (copy this):

Install the sentinelone skill from https://github.com/servosity/msp-skills/tree/main/skills/sentinelone. The skill defines how its required CLI (sentinelone-cli) can be installed via the openclaw: frontmatter block.

OpenClaw isn't generally available yet; the frontmatter wiring is pre-shipped and will activate the moment OpenClaw launches.

Authenticate

Set the credentials the CLI needs (from your SentinelOne management console):

SENTINELONE_API_TOKEN=<value> sentinelone-cli doctor

doctor confirms the credentials work before you run anything that touches data. It exits 0 even when the credential is rejected, so scripts should add --fail-on error.

What this skill does

Full command reference: guide.md. For the AI-agent operating contract (--agent, --dry-run, when to confirm before mutating), see AGENTS.md.

What makes this different

Most SentinelOne integrations and MCP servers proxy each question into a live API call. That's fine for one record. It dies at scale, when you're asking "rank every open threat across all 40 client sites by confidence, severity, and age" or "which endpoints went dark or dropped to detect-only since yesterday" - questions the console only answers one scope at a time, if at all.

This skill syncs SentinelOne into a local SQLite mirror with full-text search, snapshotting history on every sync. Aggregate questions become one local SQL join: instant, offline, and the AI sees the answer, not the raw data. Compound commands like threats triage, threats blast-radius, fleet-health stale, and whatchanged join across threats, agents, sites, and stored snapshots - cross-site rollups and time-aware diffs a stateless API wrapper can't do.

The pain this closes

The SentinelOne management console scopes to one Account or Site at a time. Run it across a book of customer sites and every cross-client question - who has the worst open threats, whose agents went dark, who is stuck on an old bu