Keeper Security launches suite of specialised AI skills

Keeper Security has unveiled Keeper Agent Kit, a suite of specialised AI skills integrating Keeper Secrets Manager and Keeper Commander with AI coding agents such as Claude Code, Codex, GitHub Copilot and others.

Agents use the keeper-secrets skill to inject credentials into local runtimes, ensuring the raw secret never appears in the chat UI. Through the keeper-admin skill, agents manage users, teams and audit resources via Keeper Commander. The keeper-setup skill automates the configuration of Keeper’s security tools, establishing a secure environment for new projects from the first command.

For teams operating in hosted or orchestrated AI environments, Keeper also offers a Model Context Protocol (MCP) server integration (available in Docker and Node configurations), that enables agent platforms to retrieve secrets via a running MCP server process rather than local CLI tools.

When an AI agent uses Keeper’s CLI tools, every action taken by the agent is governed by the same rigorous role-based access controls and audit logging as a human user accessing systems through Keeper, the company stated.

"The Keeper Agent Kit provides a definitive framework for how AI agents interact with sensitive enterprise data," said Craig Lurey, Keeper Security’s chief technology officer and co-founder.

"By equipping these agents with instructions to use our encrypted CLI tools locally, we ensure the agent runs commands within the developer’s own authenticated session. This architecture maintains our zero-knowledge standard while allowing developers to leverage the full speed of AI without leaving the vault door open."

 "With the Agent Kit, we are transforming AI from a conversational assistant into a secure partner that respects the organisational security perimeter," said Jeremy London, Keeper’s director of engineering, AI and threat analytics.

“By allowing agents to resolve secrets at runtime without ever seeing the raw credential, we help close one of the most dangerous exposure points in the modern developer stack."