Claude Security adds continuous scanning and fix tracking for Enterprise

On 21 October 2026 Anthropic released a new version of Claude Security in public beta for Claude Enterprise customers. Teams create a project, connect repositories through the Claude GitHub app (including GitHub Enterprise Server) or with an access token from GitLab and other Git providers, and choose the branch and scope. Claude runs a deep baseline scan and then scans changes regularly based on their risk and complexity. A project can hold several repositories, so issues between services can be caught. Anthropic says thousands of organizations have found over a million vulnerabilities since the public beta began in April.

Open findings are checked against changed code and marked fixed when the fix lands, even if it was made outside Claude Security; if the issue appears again, the finding reopens. Each project has a knowledge base for deployment details and security policies, plus a generated threat model the team can edit, and findings are rated against it.

A new API covers projects and findings, with personal access tokens and webhooks, and Claude Security is also available as an MCP connector in Claude.ai and Claude Code. Admins enable it in the admin console and get role-based access controls. Organizations receive $25,000 in free usage credits each month for two months, for usage through December 31, 2026.