Overview
The SentinelOne Purple AI MCP Server serves as a pivotal gateway, democratizing access to the vast security context within the Singularity Platform for any generative AI application. By implementing the Model Context Protocol, this server delivers comprehensive security telemetry that includes device inventory, real-time alerts, vulnerability data, and misconfiguration findings, directly into your cloud-native workflows.
It is engineered to facilitate the creation of next-generation, agentic security solutions. AI agents can leverage SentinelOne's data lake, running PowerQueries on events and interacting directly with Purple AI for conversational threat analysis and guided security actions. This capability accelerates the shift to an autonomous Security Operations Center (SOC) model, where agents can automatically perform incident enrichment, validate security posture, and inform strategic decisions across enterprise and cloud assets. The Purple AI MCP Server provides the essential integration layer for embedding true security intelligence into your custom AI systems.
To learn more about this open-source resource and explore its deployment capabilities, visit the official project page at: https://github.com/Sentinel-One/purple-mcp Purple AI MCP Server is also deployable as an EKS and through Amazon Bedrock, using Agent Core.
Users will need to have an active deployment of SentinelOne console and be able to obtain the SentinelOne Singularity Console token and url to be able to deploy and use the Purple AI MCP server.
Highlights
- The Purple AI MCP Server uses the open-source Model Context Protocol (MCP) to establish a universal, standardized bridge, connecting the SentinelOne Singularity Platform with any AI framework or LLM.
- It exposes comprehensive, read-only security services, including Purple AI for conversational security investigation, Alerts, Vulnerabilities, Misconfigurations, Events (PowerQuery), and Asset Inventory to enrich AI-native workflows.
- Empowers developers and partners to build custom, context-aware agentic AI use cases for security operations (SecOps), enabling autonomous threat triage, real-time posture analysis, and advanced threat hunting.
Details
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Trust Center
Financing for AWS Marketplace purchases
Pricing
Vendor refund policy
All fees are non-cancellable and non-refundable except as required by law.
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
ECS
- Amazon ECS
Container image
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
Latest build of SentinelOne Purple AI MCP Server. Please see https://github.com/Sentinel-One/purple-mcp for additional release notes
Additional details
Usage instructions
###Obtaining SentinelOne Console Token
A SentinelOne Console Token is required for using MCP Server. Before deploying Purple AI MCP you need to have an active deployment of Purple AI Singularity Operations Center. If you are not registered with the SentinelOne Singularity Platform, please visit https://www.sentinelone.com/platform/Â for more information on subscribing.
Obtain a Sentinelone Singularity Operations Center console token. This can be found in SentinelOne Console Policy & Settings > User Management > Service Users in your console. Currently, this server only supports tokens that have access to a single Account or Site. If you need to access multiple sites, you will need to run multiple MCP servers with Account-specific or Site-specific tokens.
###Deployment instructions quickstart:
- Create a new ECS Cluster
- Create a new task definition that includes the below environment variables and ensure container exposes port 8000
PURPLEMCP_CONSOLE_BASE_URL=https://your-console.sentinelone.net PURPLEMCP_CONSOLE_TOKEN=your-token MCP_MODE=streamable-http PURPLEMCP_STATELESS_HTTP=True
- Create a new service using the task definition created in step 2.
For further usage instructions see deployment guideÂ
###Example deployment using Docker:
docker run -p 8000:8000 \ -e PURPLEMCP_CONSOLE_TOKEN \ -e PURPLEMCP_CONSOLE_BASE_URL \ -e MCP_MODE=streamable-http \ -e PURPLEMCP_STATELESS_HTTP=True \ 709825985650.dkr.ecr.us-east-1.amazonaws.com/sentinelone/sentinelone/purple-ai-mcp-server:0.6.0####Example Payload 1 - Listing available tools
{ "jsonrpc": "2.0", "id": 1, "method": "tools/list", "params": { "_meta": { "progressToken": 1 } } }Expected Output
{ "jsonrpc": "2.0", "id": 1, "result": { "tools": [ { "name": "purple_ai", "description": "Query Purple AI for information and assistance", "inputSchema": { "type": "object", "properties": { "query": { "type": "string", "description": "The question or request to send to Purple AI" } }, "required": ["query"] } } ] } }####Example Payload 2 - Query Purple_AI
{ "jsonrpc": "2.0", "id": 2, "method": "tools/call", "params": { "name": "purple_ai", "arguments": { "query": "What is Purple AI?" } } }Expected Output 2
{ "jsonrpc": "2.0", "id": 2, "result": { "content": [ { "type": "text", "text": "text response" } ], "isError": false } }Support
Vendor support
Multiple support options are available. Email support at support@sentinelone.comÂ
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.