The capability is in public beta for Claude Enterprise customers, according to the supplied source.
Teams create a project, connect repositories through the Claude GitHub app, including GitHub Enterprise Server, or use access tokens for GitLab and other Git providers. After a baseline scan, Claude re-scans code changes according to risk and complexity. A project can contain multiple repositories. Findings are marked resolved when changed code fixes them, including fixes made outside Claude Code, and reopen if the vulnerability recurs.
The update also includes an API for projects and findings, webhooks, role-based project controls, and an MCP connector for Claude and Claude Code. Teams can add deployment practices, policies, and controls to a project knowledge base; Claude generates an editable threat model from code and that context. The source says organizations receive $25,000 in monthly usage credits for two months, applicable through December 31, 2026.
The source does not establish a permanent price, detection accuracy, false-positive rate, or how frequently scans run in practice.