Genea brings AI agents to access control with role-based permissions
Genea has announced the release of Genea MCP, a Model Context Protocol (MCP) server that connects AI agents directly to the Genea Access Control platform. Onboarding a new hire, setting up a contractor for two weeks, or unlocking the loading dock now takes one sentence instead of a dozen clicks. Genea is one of the first access control providers to launch a native MCP server.
Most access control work isn’t hard, but it can be tedious. Adding one person to one site means finding the location, picking the access group, entering their details, and confirming the change. Repeat that for every new hire, contractor, and access change, and IT and security teams lose hours every week to routine clicks.
Genea MCP skips the clicking. Ask it to “give Jordan access to the third floor,” and it finds the right location and access group, asks only for what it can’t look up itself, does the work, and confirms what changed. Teams can manage people, temporary access, access groups, doors, and controllers without opening the portal.
“Access control software has always made administrators learn the system,” said Michael Wong, CEO and President of Genea. “Genea MCP flips that. Your team says what needs to happen, and Genea does it within the permissions that person already has. In physical security, speed only matters if control comes with it, so we built the controls first.”
Built so AI never has more control than the person using it
Genea MCP is off by default and must be enabled by an administrator for both the account and the user’s role. Once on, it inherits each user’s existing Genea permissions, checked on every request, so there is no second permission system to manage. Before any high-impact action, such as deleting a user or revoking access, it shows exactly what will be affected and waits for a yes.
“The first question every IT team asks is who can use this and what they can do with it,” said Mike Maxsenti, SVP of Product at Genea. “The answer is short. Only the people an administrator turns it on for, and only what their role already allows. That’s what let’s security teams say yes.”
