Updates include Network Detection, AI Chart Builder and an AI Playbook, with integrations for third-party AI tools via the MCP standard.
SEON has rolled out new AI capabilities for its fraud prevention and AML compliance platform, including a Model Context Protocol (MCP) server designed to connect SEON data to external AI tools. The company said the MCP server, Network Detection, AI Chart Builder and an AI Playbook for Risk and Compliance Teams are available now to SEON customers.
The MCP server is positioned as a way for analysts to use third-party AI tools while pulling investigation context from SEON. SEON said analysts can connect tools including Claude, ChatGPT, Gemini and Microsoft Copilot to “900+ real-time risk signals spanning identity, device, behavioral, AML and IP data,” with signals accessible “in a single call” via the open MCP standard.
“The software world is moving toward a headless model, where teams don’t need to live inside a vendor’s dashboard to get full control over data and functionality,” said Tamas Kadar, CEO and Co-Founder, SEON. “Our job is to be the best command center for fraud, risk and compliance intelligence. We’re giving analysts the freedom to use whichever AI tools work best for them.”
SEON also introduced Network Detection and AI Chart Builder inside its platform. Network Detection builds on SEON’s network analysis features released last year, and “continuously scans the last two months of transactions across devices, emails, phone numbers and IP addresses” to surface suspicious clusters. AI Chart Builder generates data visualizations from natural-language questions using live SEON data, targeting reporting and dashboarding needs typically handled through BI teams or spreadsheet exports.
Customer TurboTenant said it is already using the MCP approach in production workflows. “The SEON MCP integration has fundamentally changed how our risk analysts operate,” said Eric Taylor, Manager of Trust and Safety, TurboTenant. “Before, they had to manually pull data across multiple systems to piece together what happened. Now, we pull a user’s entire platform journey and all of SEON’s risk signal context directly into Claude, and AI connects the dots on complex fraud patterns without us doing that assembly. It’s opened up OSINT capabilities that wouldn’t have been possible before.”
To support adoption, SEON said it is shipping an AI Playbook for Risk and Compliance Teams alongside the releases, including “pre-built agentic skills” such as a fraud analyst daily briefing and a decline spot-check, compatible with the MCP server. “SEON opening its data layer to any AI we want to use is exactly the kind of architectural decision that fits where the market is going,” said Mostafa Hassanin, CISO, SMG Marketplace.
