Skip to main content
Glama
Sentinel-One

Purple AI MCP Server

Official
by Sentinel-One

purple_ai

Ask natural language questions to investigate threats, generate PowerQueries, and get answers about SentinelOne security incidents.

Instructions

Interact with SentinelOne's Purple AI, a cybersecurity assistant that helps you investigate threats, generate PowerQueries, and answer questions about SentinelOne. Purple AI understands natural language and converts your questions into structured security queries, or answers in plain language.

What Purple AI can do:

  • Generate and explain PowerQueries for threat hunting and detection

  • Help answer questions using threat intelligence and behavioral signals

  • Explore user, process, network, and file-based activities

  • Investigate MITRE TTPs, ransomware behavior, lateral movement, and more

  • Answer questions about SentinelOne capabilities

What Purple AI can't do:

  • Access active alerts (use the Alerts tool for that)

  • Modify configurations or directly interact with your endpoints

  • Run the PowerQueries itself (use the PowerQuery tool to run the PQ returned by Purple AI)


How to ask good questions

Purple AI works best when your questions are:

  • Descriptive: Include process names, file paths, domains, ports, or usernames

  • Focused: Describe what you're trying to understand or find

  • Scoped: If helpful, include filters like time ranges, endpoint type, or OS

Example questions:

  • Show me PowerShell processes that connected to external IPs

  • Find unsigned processes that accessed lsass.exe

  • List endpoints where the user “jsmith” logged in more than 5 times

  • Are there any reverse SSH tunnels from public IPs?

  • Find living-off-the-land binaries spawned from Microsoft Word

DO NOT instruct Purple AI to "Generate a Powerquery to ...". Instead, just say what you are looking for. Example: - GOOD: "Is APT-1337 in my environment?" - BAD: "Generate a PowerQuery to determine if APT-1337 is in my environment, including their typical tools, processes, and TTPs."

Tips for writing questions

  • Start with verbs like: show, find, list, search

  • Add specific entities like: powershell, svchost, lolbins, ssh, .tmp files

  • Use filters like: external IPs, non-Windows folders, file size over 1GB

  • Ask about behaviors: ransomware, persistence, privilege escalation, data staging, beaconing, phishing

  • If you want a PowerQuery, specifically say "generate a powerquery for " -> Example: "Generate a PowerQuery to detect Wizard Spider threat group indicators"

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, but the description thoroughly discloses what the tool can and cannot do, input format expectations, and behavioral traits such as not accessing alerts or modifying configurations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Despite length, the description is well-structured with clear sections (can/cannot do, how to ask, examples, tips). Every sentence adds value and the purpose is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the minimal input schema and existence of output schema, the description provides complete guidance on usage, expected inputs, and tool behavior, enabling correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only one parameter 'query' with no schema description coverage, but the description compensates with extensive guidance on query content, including example questions and tips, adding significant meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool interacts with SentinelOne's Purple AI for threat investigation, generating PowerQueries, and answering cybersecurity questions. It distinguishes itself from siblings like powerquery and alert tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly lists capabilities and limitations, provides detailed guidance on how to ask effective questions with examples, and warns against instructing the tool to generate a PowerQuery, instead asking for what is needed directly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Sentinel-One/purple-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server