New MCP server, Network Detection, AI Chart Builder and AI Playbook give fraud and AML teams more ways to put AI to work

SEON, the AI Command Center for Fraud Prevention and AML Compliance, has built a platform where flexibility is an accent of its architecture. With SEON, customers can ingest any custom field or data type, build any rule or alert they need, and investigate in system driven workflows that represent the way their team operates. Most importantly, they can choose a rules-based policy, one driven by AI or a hybrid decisioning model that leverages both. SEON has the capabilities to meet teams how and where they actually operate.

Today, the company extends that same flexibility to the use of AI in the fight against fraud and financial crimes. A Model Context Protocol (MCP) server opens SEON’s data layer to whichever AI tool a team prefers. Two additional capabilities, Network Detection and AI Chart Builder, connect SEON’s existing capabilities in automation and business intelligence. To support adoption, an AI Playbook for Risk and Compliance Teams ships alongside them, giving customers a practical starting point for putting their MCP connection to work quickly.

Access to AI Has Outpaced Access to Risk Data

For most fraud and AML teams, AI is accessible but still hard to put to real work. Analysts have ChatGPT, Claude or Gemini at their fingertips. What they don’t have is a clean way to get their investigation data into those environments. Instead, they manually paste in transaction records, customer profiles and risk signals, losing context at every step and creating security risks for their organization. According to the 2026 Fraud and AML Leaders Report, 98% of fraud and AML leaders are already using AI in their workflows. The tools are there. The data pipeline is not.

An Open Foundation for Any AI Tool

SEON’s MCP server addresses that gap. Analysts can link Claude, ChatGPT, Gemini, Microsoft Copilot or any custom agent to SEON’s 900+ real-time risk signals spanning identity, device, behavioral, AML and IP data. All signals are accessible in a single call, so the AI spends its token budget and processing time on analysis rather than pulling data from multiple systems. Because the integration uses the open MCP standard, customers are free to use whatever works best today and switch to a stronger option tomorrow without rebuilding anything.

“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.”

“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.”

Meeting Teams Where They Are

Some customers are ready to run their entire risk operation through an agentic platform. Others want AI working inside the SEON interface they already use. Most are somewhere in between. SEON supports all team preferences, whether they work inside the platform or outside it.

Network Detection builds on the network analysis SEON released last year, including Similarity ranking and the Network graph. It continuously scans the last two months of transactions across devices, emails, phone numbers and IP addresses to identify clusters that are only suspicious when viewed together. Coordinated fraud rings and money laundering networks now surface before an analyst opens an alert.

AI Chart Builder turns natural-language questions about your business into instant data visualizations. Analysts no longer wait on business intelligence teams for dashboard projects or are forced to rebuild reports from spreadsheet exports. They ask a question and the chart appears, built on live SEON data.

These join an AI portfolio SEON has shipped over the past year. Existing capabilities include AI-assisted rule creation, scoring insights, AML screening analysis, automated case summaries and regulatory report generation.

“The next generation of fraud and KYC challenges won’t look like the last one. AI agents will interact with our marketplaces as customers, and AI agents will be used to impersonate and exploit our customers as well. Our team needs an intelligence foundation that’s ready for both,” said Mostafa Hassanin, CISO, SMG Marketplace. “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.”

A Fast-Start Kit for Teams Ready to Build

To help teams get started quickly, SEON is also releasing an AI Playbook for Risk and Compliance Teams. The playbook is a practical guide to connecting AI tools to SEON and building investigation workflows that match how analyst teams actually operate. It ships with pre-built agentic skills, including a fraud analyst daily briefing and a decline spot-check, both compatible with SEON’s MCP server and ready to deploy on day one.

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