Celigo has launched MCP Management to govern how AI assistants and agents access business systems. The product is aimed at IT and security teams that need oversight of AI activity across enterprise software.

The offering provides a single control layer for both Celigo-built and third-party Model Context Protocol servers, which are increasingly used to let AI tools connect with software across the business. It enables teams to authenticate users, define access at the level of individual tools and maintain an auditable record of AI activity.

Model Context Protocol, or MCP, has emerged as a standard for linking AI assistants and agents to business systems. Software suppliers have begun offering their own MCP servers, with each server exposing specific actions an AI tool can carry out, such as checking a customer record in a CRM system, reviewing an invoice in an ERP platform or updating a service ticket.

That expansion has widened access beyond specialist integration teams to employees using assistants such as Claude, ChatGPT, Copilot and Cursor, as well as autonomous agents that can act without direct human input. Celigo argues this shift has created governance problems because many MCP servers rely on broad default access and shared service credentials, making it harder to identify who was behind a specific action.

Matt Graney, Chief Product Officer at Celigo, said the company was addressing a gap in enterprise controls around AI-based actions.

"AI assistants and agents are a new class of actors in the enterprise, and the old model of shared credentials and broad access was never designed for them.

Source link