An interactive setup wizard for Model Context Protocol (MCP) servers is now available, making configuration in Claude much simpler, and persistent shell fixes have also been released.
Custom slash commands and MCP debug mode: markdown files in custom slash command directories can now be recognized and inserted directly into conversations, while a new debug mode for the Model Context Protocol provides comprehensive error details for administrators and engineers.
A recent software update has improved user-friendliness and security in three key areas, including the addition of an ANSI color scheme that significantly enhances display and rendering quality in terminal environments.
The platform added three new features to improve tool management and command recognition: the `/approved-tools` command for more granular control over tool permissions, word-level diff display for more detailed code comparisons, and fuzzy-matching support for slash commands.
Fuzzy matching for command entries improves user experience by enabling systems to accurately identify and execute `/commands` even when input is imprecise or incomplete.
Plugin dependencies are now enforced, background sessions preserve model and effort level, and various crashes and UI issues on Windows and macOS have been fixed.
Claude Code v2.1.142 introduces eight new agent flags, uses Opus 4.7 as the standard for Fast Mode, and fixes critical bugs affecting background sessions on macOS and Windows.
Anthropic and the Gates Foundation are jointly investing $200 million in AI applications for global health, with a four-year partnership focused on improving healthcare in low- and middle-income countries and supporting vaccine development.
The version improves hook integration for terminal events, adds identity federation support, and closes 20+ bugs in permission dialogs, history management, and renderer logic.
Anthropic introduces Claude for small businesses: integration into established business tools with 15 workflows and 15 skills for finance, operations, and marketing, aiming to promote AI adoption among SMEs with limited staff resources.
Claude Code v2.1.140 fixes critical bugs in agent tooling, background service management, and settings reload, including connection drops and token refresh errors in remote settings.
Claude Cowork and Claude Code share the same agent loop but differ in security risk: Cowork offers more features with a larger attack surface, while Code runs in an OS sandbox. Enterprises must assess these differences when deploying.
