How Claude Code’s Safe Mode Finds What Broke Your Config
Claude Code’s new –safe-mode flag (v2.1.169) boots with all your customizations off, so you can isolate which setting broke things.
mcp
Claude’s Managed Agents Now Run Inside Your Corporate Network
Anthropic shipped self-hosted sandboxes and MCP tunnels for Claude Managed Agents, so code and internal systems never leave your network — the likely unlock for enterprise adoption.
Claude Can Now Reach Your Internal Database: MCP Tunnels Launch
Anthropic shipped two new security features for Claude Managed Agents — MCP Tunnels and Self-Hosted Sandboxes. Agents can now reach internal systems without poking holes in your firewall.
Claude Agents Move Into Company Infrastructure — Two London Reveals
Anthropic’s London keynote added two features to Managed Agents: self-hosted sandboxes and MCP tunnels. Now you can run Claude agents without sending code or files outside your network.
Anthropic Now Holds the SDK Tooling Behind OpenAI Too — What the Stainless Deal Means
Anthropic acquired Stainless, the SDK auto-generation startup also used by OpenAI, Google, and Cloudflare. Reported price: $300M+. The next battleground is connection infrastructure.
Claude Hits the Lawyer’s Desk — Today’s AI Roundup
Anthropic launched Claude for Legal with 20+ MCP connectors and 12 practice plugins. Google embedded Gemini Intelligence into Android, and GPT-5.5 Instant became ChatGPT’s default.
VS Code Quietly Added Copilot as a Co-Author on Your Commits
VS Code 1.118 silently injected a Copilot co-author trailer into commits — rolled back in 1.119. Plus a Linux RAT hunting DevOps creds and the largest Canvas LMS breach to date.
5 Hidden Claude Code Features That Doubled My Productivity — /btw, Plan Mode, and CLAUDE.md Done Right
Five Claude Code features most users miss: /init, Plan Mode, /btw, /clear, and MCP. Small habits that cut wasted context and rewrites in half.