Securing Claude Code: The New Compliance API, Local Visibility, and Identity Governance
Anthropic's new Compliance API endpoints expose Claude Code local session transcripts, highlighting governance gaps for endpoint AI agents.
Anthropic added local session transcript endpoints to its Compliance API on August 11, 2026, giving security teams visibility into prompts, bash commands, file operations, and MCP commands run by Claude Code harnesses on endpoints. The article argues local harnesses break the classic shared-responsibility model, citing Token Security data that 68.6% of discovered AI agents run on endpoints, and a Cloud Security Alliance survey of 418 IT and security professionals in which 82% found an unknown agent within the past year. It outlines three governance layers: Anthropic managed settings as a policy baseline, the Compliance API for cloud-visible transcripts, and endpoint telemetry to connect agent activity to identity, credentials, and permissions.
- New endpoints: /v1/compliance/apps/sessions/local list, detail, and message transcript retrieval.
- Text, tool_use, and tool_result blocks cover user prompts, bash commands, and MCP activity.
- Managed settings JSON/registry records enforce MCP allowlists and bash regex baselines across sessions.
- Local agents accounted for 68.6% of AI agents Token Security discovers in customer environments.
- CSA survey: 82% of 418 respondents discovered an agent unknown to security or IT in the past year.
- Products
- Claude CodeClaudeCompliance API
- AI models
- Claude
From the original article
9 min read at thehackernews.com
Claude Code reads files, runs shell commands, invokes MCP tools, and acts through the credentials available on a developer’s machine. Anthropic’s new Compliance API endpoints give security teams their clearest view yet into that activity. They also expose a larger problem: activity logs alone cannot tell you whether an agent’s access is legitimate.
By @TheHackersNews · thehackernews.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.