SentinelOne MCP Server
for AI Agents
Connect your AI agent to StackOne's SentinelOne MCP server and give it 69 MCP tools out of the box. Auth, tool execution, and security all managed.
StackOne 
Coverage
69 Agent Actions
Agents can read, write and delete in SentinelOne. Extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your SentinelOne MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every SentinelOne tool response scanned for prompt injection in milliseconds, with 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every SentinelOne call.
Tools Discovery →What is the SentinelOne MCP Server?
A SentinelOne MCP server lets AI agents read and write SentinelOne data through the Model Context Protocol, Anthropic's open standard for connecting LLMs to external tools. StackOne's SentinelOne MCP server ships with 69 pre-built actions, fully extensible via the Connector Builder, plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All SentinelOne MCP Tools
Every StackOne action for SentinelOne, ready for your agent. Read, write and delete, scoped to exactly what you need.
Accounts
- List Accounts
List the SentinelOne accounts the token can see.
- Get Account
Get a SentinelOne account by ID.
Agent Tags
- Create Agent Tag
Create an endpoint tag that can then be attached to agents.
- List Agent Tags
List the endpoint tags defined in the tenant.
Groups
- Create Group
Create an endpoint group inside a site.
- List Groups
List the endpoint groups in the SentinelOne tenant.
- Get Group
Get one SentinelOne endpoint group by ID.
- Update Group
Update a SentinelOne endpoint group.
- Delete Group
Delete a SentinelOne endpoint group.
Unified Organizations
- List Unified Organizations
List unified organizations in a SentinelOne console.
- Get Unified Organization
Get a unified SentinelOne organization by ID.
Unified Roles
- List Unified Roles
List unified roles in a SentinelOne console.
- Get Unified Role
Get a unified SentinelOne role by ID.
Unified Users
- List Unified Users
List unified users in a SentinelOne console.
- Get Unified User
Get a unified SentinelOne user by ID.
Roles
- List Roles
List the roles defined in a SentinelOne console.
- Get Role
Get a SentinelOne role definition by ID.
Service Users
- List Service Users
List the SentinelOne service users, the API-only identities.
- Get Service User
Get a SentinelOne service user by ID.
Sites
- Create Site
Create a site in the SentinelOne tenant.
- List Sites
List the sites in the SentinelOne tenant.
- Get Site
Get one SentinelOne site by ID.
- Update Site
Update a SentinelOne site.
- Delete Site
Delete a SentinelOne site.
Threat Notes
- Create Threat Note
Add an analyst note to the selected threats.
- List Threat Notes
List the analyst notes recorded against one threat.
- Update Threat Note
Change the text of one analyst note on a threat.
- Delete Threat Note
Delete one analyst note from a threat.
Users
- List Users
List the users who can sign in to the SentinelOne console.
- Get User
Get a SentinelOne console user by ID.
Other (39)
- Add Threats To Blocklist
Block the file hashes behind the selected threats across a scope.
- Add Threats To Exclusions
Create an exclusion from the selected threats so SentinelOne stops flagging them.
- List Activities
List console and agent activity records, the audit trail of the SentinelOne tenant.
- List Activity Types
List the activity type codes used by SentinelOne, with the description of each.
- List Agents
List the SentinelOne agents installed on managed endpoints.
- List Agent Applications
List the applications installed on specific endpoints.
- Get Group Registration Token
Get the registration token that enrols new agents straight into a group.
- Get Unified Credentials
Get the current SentinelOne connection's unified credentials and identity.
- Get Site Registration Token
Get the registration token that enrols new agents into a site.
- List Threats
List the threats SentinelOne has detected on managed endpoints.
- Get Threat Timeline
Get the ordered history of what happened to one threat.
- List Threat Events
List the endpoint events recorded around one threat.
- Get Threat Exclusion Options
Get the exclusion types that can be created from one threat's detection data.
- Get Current User
Get the user that owns the connection API token.
- Set Agent External ID
Set the customer identifier shown on the selected endpoints.
- Move Agents To Site
Move the selected endpoints to another site.
- Update Agent Software
Update the SentinelOne agent version on the selected endpoints.
- Move Agents To Group
Move selected agents into an endpoint group.
- Update Threat Analyst Verdict
Record the analyst's judgement on the selected threats.
- Update Threat Incident Status
Move the selected threats through the triage workflow.
- Update Threat External Ticket ID
Link the selected threats to a ticket in another system.
- Initiate Agent Scan
Start a full disk scan on the selected endpoints.
- Abort Agent Scan
Stop a running full disk scan on the selected endpoints.
- Disconnect Agents From Network
Isolate the selected endpoints from the network.
- Connect Agents To Network
Return the selected endpoints to the network after isolation.
- Restart Agents
Restart the machines behind the selected endpoints.
- Shut Down Agents
Shut down the machines behind the selected endpoints.
- Uninstall Agents
Uninstall the SentinelOne agent from the selected endpoints.
- Decommission Agents
Decommission the selected endpoints and remove them from the console.
- Mark Agents Up To Date
Mark the selected agents as running an up to date version.
- Approve Agent Uninstall
Approve pending uninstall requests from the selected endpoints.
- Reject Agent Uninstall
Reject pending uninstall requests from the selected endpoints.
- Fetch Agent Installed Applications
Ask the selected endpoints to report their installed applications.
- Fetch Agent Logs
Collect diagnostic logs from the selected endpoints.
- Manage Agent Tags
Add, remove or override endpoint tags on the selected endpoints.
- Count Agents
Count the agents that match a filter, without returning the agents themselves.
- Mitigate Threats
Apply a mitigation action to the selected threats.
- Fetch Threat File
Retrieve the file behind the selected threats for offline analysis.
- Check Connection
Check that the API token can read users from the SentinelOne console.
Set Up Your SentinelOne MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to SentinelOne in under 10 lines of code.
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}Platform Resources
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
MCP vs A2A: Architecture, Security, and When to Use Each
MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.
12 min
MCP vs API: What Hundreds of Connector Builds Taught Us
MCP wraps APIs, it doesn't replace them. After building hundreds of connectors that serve both, here's when each approach wins.
14 min read
SentinelOne MCP Server FAQ
Does StackOne have a SentinelOne MCP server?
SentinelOne MCP server vs direct API integration: what's the difference?
How does SentinelOne authentication work for AI agents?
origin_owner_id.Are SentinelOne MCP tools vulnerable to prompt injection?
What is the context bloat of a SentinelOne agent and how do I avoid it?
Can I limit which actions my SentinelOne agent can access?
Can I create custom agent actions for my SentinelOne MCP server?
When should I NOT use a SentinelOne MCP server?
What AI frameworks and AI clients does the StackOne SentinelOne MCP server support?
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.