Verisk Analytics is embedding its insurance analytics capabilities into Anthropic’s Claude models through new Model Context Protocol (MCP) connectors, enabling underwriters and claims professionals to interact with data using natural language within enterprise AI environments.
The integration allows Verisk’s datasets to be accessed directly Claude, reducing the need for users to switch between multiple systems and improving workflow efficiency across underwriting and claims functions.
Initial use cases include underwriting intelligence, which provides conversational access to loss cost trends and filing signals from Insurance Services Office to support pricing and risk assessment, and XactRestore, which offers natural language access to property repair pricing and estimating data commonly used in claims workflows.
Verisk noted that the solution is designed to operate within governed environments, maintaining existing controls, regulatory compliance, and human oversight in decision-making processes.
“Trust is the foundation of insurance, and that doesn’t change as new technologies emerge. What is changing is how professionals expect to interact with information. Our role is to bring AI into insurance in a way that reflects the realities of the industry – where data must be authoritative, decisions must be explainable, and accountability remains with people. This collaboration with Anthropic applies a conversational interface to Verisk’s governed analytics so professionals can work more efficiently, while upholding the industry’s high standards.” – Lee Shavel, president and CEO of Verisk.
