AI Briefing#claude-desktop
The latest AI and developer news about #claude-desktop, with the original source and a short summary.
The latest AI and developer news about #claude-desktop, with the original source and a short summary.
Anthropic shipped automatic per-folder groups within a day of the update but removed the changelog and activity stats, causing workflow disruptions for power users.
A proxy attack exploiting Claude Desktop's MCP connector permissions and a DeepSeek-based ransomware PoC have been reported.
Fabrica-STAR, an open-source tool that checks security vulnerabilities in Claude Desktop and MCP servers, has been released.
It has been confirmed that when using the permission-skip flag in Claude Desktop, sensitive data theft and persistent attacks are possible even when Bash is blocked.
cdo, an open-source tool that lets you use local Ollama models while keeping the Claude Desktop UX, has been released.
1mcp manages MCP settings for multiple AI clients in one place and blocks tool schema changes.
Claude Desktop automatically installed a Native Messaging host into multiple Chromium browsers on macOS.
The Opus 4.6 model has been removed from Claude Desktop's Code tab, raising concerns about increased token consumption.
A case study implementing an MCP server using only Windows Notepad and a built-in runtime.
Claude Desktop turned MCP server installation into a single-button action with .mcpb extensions.