Swimlane Adds Custom Detection, Two-Way MCP Support and AI Application Builder to Turbine

Swimlane has expanded its Turbine platform with custom detection capabilities, two-way MCP support and an AI-powered application builder to help security teams address emerging threats and automate security operations.
https://swimlane.com/
Swimlane's Turbine platform adds custom detection, MCP connectivity and AI-powered application building capabilities for security teams.

Swimlane's Turbine platform adds custom detection, MCP connectivity and AI-powered application building capabilities for security teams.

Swimlane has introduced new capabilities to its Turbine platform that allow security teams to run custom detection logic against large volumes of data and send resulting alerts directly to Swimlane AI SOC for investigation and response.

The October release also adds two-way Model Context Protocol (MCP) support and a new Hero AI agent that uses natural-language prompts to build applications. The updates expand how security teams connect tools, develop workflows and automate security operations.

The new detection capabilities address emerging risks associated with enterprise adoption of AI agents, MCP servers, copilots and local models. Threats such as prompt injection, unsanctioned AI use, compromised guardrails and other AI-specific activity may fall outside vendor-defined detection capabilities, leaving security teams without alerts for investigation.

Swimlane's latest Turbine capabilities allow organizations to apply their own detection logic to these risks, including scenarios where AI systems themselves are the subject of a security incident.

The platform's big data processing capabilities allow security teams to evaluate tens of thousands of records in a single action across parallel compute nodes. Organizations can use customer-defined detection logic to identify activity specific to their environments and send resulting alerts directly into Swimlane AI SOC for agentic investigation and governed response.

"The security industry has spent the last two years debating how autonomously AI can work an alert, but that skips a more basic question: where did the alert come from?" said Cody Cornell, Co-Founder and CEO of Swimlane. "As AI introduces new risks faster, investigation depth and quality are going to become essential, vendor-defined detections alone don't paint the full picture, the teams closest to those environments need a way to define what matters to them. Turbine gives them that control, then connects the resulting alert directly to investigation and response."

The detection capabilities extend Turbine further into the detection-to-response lifecycle without replacing existing security technologies. The platform continues to consume alerts from SIEM, EDR, cloud security and other tools while providing an additional way for organizations to evaluate available data using their own detection logic.

Use cases include detecting local AI model usage, unsanctioned AI accounts, sensitive data submitted to AI services, prompt injection and disabled or bypassed guardrails. Teams can also describe desired detections in natural language and use Turbine's playbook generation capabilities to help build the corresponding detection logic.

The October release also expands MCP support in both directions, allowing AI agents to access external tools and outside AI clients to invoke governed automation within Turbine.

Through its role as an MCP host, Turbine allows Hero AI to connect directly to third-party MCP servers and use their tools during investigations and playbooks. Authentication and access are managed centrally.

As an MCP server, Turbine allows external AI agents and assistants, including Claude, ChatGPT, Cursor, Gemini CLI and Microsoft Copilot, to invoke governed Turbine components such as multi-step playbooks within existing role-based access controls.

The platform also bridges MCP tools and APIs, connecting Swimlane's integrations with external MCP-compatible tools and workflows.

"MCP is most useful when it becomes part of the operating model, not just another integration," said Srikant Vissamsetti, Chief Operating Officer at Swimlane. "Turbine can use tools from external MCP servers, expose governed automation back to AI clients and combine both with the API integrations customers already rely on. That gives security teams a practical way to bring agents into real workflows without giving up the controls and automation already in place."

Another addition is a Hero AI agent for application building. The capability allows users to create and modify applications, record structures, layouts and workflows using natural-language prompts, reducing the manual work involved in developing and adapting applications for new security use cases.

AI-generated changes remain unsaved until users review them. Proposed edits are highlighted, allowing users to accept or reject changes before they are saved.

The new capabilities build on Swimlane AI SOC and its intelligent routing model, which directs work to deterministic automation, AI-assisted investigation or fully agentic investigation based on the level of reasoning required. Customer-defined detection adds another entry point by allowing organizations to establish specific conditions that trigger investigation and response.

Swimlane said the expanded capabilities allow security teams to combine their own data and expertise with AI and deterministic automation within a governed platform rather than replacing existing detection technologies or routing every task through an AI model.

The new Swimlane Turbine capabilities, including customer-defined detection logic, two-way MCP support and the Hero AI Application Builder Agent, are now generally available.