New post! We built the MCP Policy Engine (@harvey ) to govern how agents use MCP tools.
Our approach draws on agent security research and treats prompt injection as an information flow control problem. We enforce policies outside the model based on tool capabilities and agent
Runtime controls add another layer of protection for Harvey and its customers by governing tool access, information flow, and agent actions beyond the initial connector review.
Article
Building Harvey’s MCP Policy Engine
Legal teams work across research platforms, document management systems, and communication tools. Connecting Harvey Agents to those systems gives them more context and more ways to help users complete
