SEON opens MCP server to link AI to 900+ fraud signals

SEON announced it has launched a Model Context Protocol (MCP) server that connects external AI models — including Claude, ChatGPT, Gemini and Microsoft Copilot — and custom agents to more than 900 real-time fraud and anti-money laundering (AML) risk signals. The company also introduced Network Detection, an AI Chart Builder and an AI Playbook for risk and compliance teams. The features are available now to customers.

The MCP server opens SEON’s data layer so analysts can submit a single request that includes identity, device, behavioral, AML and IP signals to an external AI. SEON noted the integration follows the open MCP standard, allowing teams to use different AI providers and switch providers without rebuilding their data pipelines.

SEON stated the single-request approach reduces manual copying of transaction records and risk context into chat tools and keeps investigation data inside secured channels.

Network Detection continuously scans the previous two months of transactions across devices, email addresses, phone numbers and IP addresses to identify clusters of linked activity. SEON described the feature as intended to surface coordinated fraud rings and money-laundering networks that may not appear in individual alerts.

AI Chart Builder translates natural-language questions into live data visualizations drawn from SEON’s platform, so analysts can generate charts on demand without exporting spreadsheets or waiting for separate business intelligence reports.

The AI Playbook for Risk and Compliance Teams ships with pre-built agent skills such as a fraud analyst daily briefing and a decline spot-check. SEON said the playbook and skills work with the MCP server and are designed to help teams deploy agent-driven workflows quickly.

Tamas Kadar, SEON’s CEO and co-founder, noted: “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.” Eric Taylor, manager of trust and safety at TurboTenant, recounted that the MCP integration changed analysts’ workflows by allowing a user’s full platform journey and SEON risk signals to be pulled into Claude so AI can connect patterns across data sources. Mostafa Hassanin, CISO at SMG Marketplace, observed that opening the data layer to external AI aligns with market demand and prepares teams for interactions with automated agents.

SEON has released AI capabilities over the past year, including AI-assisted rule creation, scoring insights, AML screening analysis, automated case summaries and regulatory report generation. The company cited the 2026 Fraud and AML Leaders Report showing 98% of fraud and AML leaders use AI in their workflows and noted that the remaining challenge is feeding investigation data into those tools securely and with complete context.

The MCP server, Network Detection, AI Chart Builder and AI Playbook are available now to SEON customers.