Updatespage 4 of 7
Claude product updates
209 articles
MCP 2026-07-28 Released as Largest Protocol Update Yet
Anthropic's official @ClaudeDevs account on X announced 'MCP 2026-07-28,' a new version of the Model Context Protocol. The update makes MCP stateless, simplifying the deployment and scaling of remote servers.
Opus 5 Now Available on All Paid Plans and the API
Anthropic has released Opus 5 across all paid plans and the Claude API. It is priced the same as Opus 4.8, serves as the default model on Claude Max, and is the strongest model available on Claude Pro. A Fast mode running about 2.5 times the default speed is also offered.
Opus 5 Sets New State-of-the-Art in Coding and Knowledge Work Evaluations
Anthropic's official account @claudeai announced on X that Opus 5 has achieved a new state-of-the-art on several coding and knowledge work evaluations. Specific benchmark names or scores were not included in the announcement.
Claude Code 2.1.219
- Added Claude Opus 5 (`claude-opus-5`), now the default Opus model — 1M context, fast mode at $10/$50 per Mtok - Added `sandbox.network.strictAllowlist` setting to deny non-allowlisted hosts for sand
Claude Code 2.1.220
- Bug fixes and reliability improvements
Claude Opus 5 launch
We launched Claude Opus 5, a thoughtful and proactive model that comes close to the frontier intelligence of Claude Fable 5 at half the price. For more information, see our blog post: Claude Opus 5.
Anthropic Announces Claude Opus 5, Near-Frontier Intelligence at Half the Price
Anthropic's official account @claudeai has announced a new model, Claude Opus 5. According to the post, Opus 5 is a thoughtful and proactive model that comes close to the frontier intelligence of Fable 5 at half the price. Specific pricing and release timeline details were not included in the announcement.
Claude Voice Conversations Now Support Opus, Sonnet, and Connected Tools
Anthropic's official @claudeai account announced that Claude's voice conversations now draw on more of the chat models available, including Opus and Sonnet. Claude can also reach tools users have connected, such as email and calendar, mid-conversation. The update is rolling out in public beta across mobile, desktop, and web.
Claude Security Plugin for Claude Code Now Available in Beta
Anthropic's official X account @claudeai announced the beta release of the Claude Security plugin for Claude Code. It lets developers scan changes for vulnerabilities before committing, or run a full codebase scan, directly from the terminal.
Claude Code 2.1.218
- Changed `/code-review` to run as a background subagent, so review work no longer fills your conversation and keeps stacked slash commands as its review target - Added screen-reader announcements of
Claude Code 2.1.217
- Added emoji shortcode autocomplete in the prompt input: type `:heart:` to insert ❤️, or `:hea` for suggestions — disable with the `emojiCompletionEnabled` setting - Added warnings when transcript wr
Claude Team Plan Now Starts at Just 2 Seats, Down From 5
Anthropic's official account @ClaudeDevs announced that the Claude Team plan's minimum seat requirement has been lowered from 5 to 2. The plan bundles shared projects, admin controls, SSO, and enterprise search.
Claude Code 2.1.216
- Added `sandbox.filesystem.disabled` setting to skip filesystem isolation while keeping network egress control - Fixed a slowdown in long sessions where message normalization cost grew quadratically
Claude Code 2.1.215
- Claude no longer runs the `/verify` and `/code-review` skills on its own; invoke them with `/verify` or `/code-review` when you want them
Claude Code Keeps Weekly Limits 50% Higher Through August 19
Anthropic's official @ClaudeDevs account announced that Claude Code's weekly usage limits will remain 50% higher through August 19. The extension applies to all Pro, Max, Team, and seat-based Enterprise users.
Claude Fable 5 Coming to Max and Team Premium Plans on July 20
Anthropic's official X account, @claudeai, announced that Claude Fable 5 will be included in all Max and Team Premium plans starting July 20, at 50% of usage limits. Pro and Team Standard users will continue to access Fable via usage credits and will receive a one-time $100 credit.
Claude Code 2.1.214
- Fixed single-segment `dir/**` allow rules like `Edit(src/**)` auto-approving writes to nested `dir/` directories anywhere in the tree instead of only `<cwd>/dir` - Fixed a permission-check bypass af
Claude Code 2.1.212
- `/fork` now copies your conversation into a new background session (its own row in `claude agents`) while you keep working; the in-session subagent it used to launch is now `/subtask` - Added `claud
Updated memory for Claude
Memory on Claude now works as a set of individual, categorized entries that Claude reads and updates during your conversations, replacing the previous daily memory summary. See Use Claude’s chat searc
Anthropic Resets 5-Hour and Weekly Rate Limits for All Users
Anthropic's official @ClaudeDevs account announced that it has reset the 5-hour and weekly rate limits for all users. This means users can now use Claude again regardless of how much of their previous limit they had used.
Claude Code 2.1.211
- Added `--forward-subagent-text` flag and `CLAUDE_CODE_FORWARD_SUBAGENT_TEXT` environment variable to include subagent text and thinking in stream-json output - Fixed permission previews relayed to c
Claude Code 2.1.210
- Added a live elapsed-time counter to the collapsed tool summary line so long-running tool calls visibly tick instead of looking stuck - Added a startup warning for `Write(path)`, `NotebookEdit(path)
HIPAA configuration for your Claude organizations is now self-serve
You can now manage HIPAA readiness for your Claude organizations yourself. This applies to both Claude Enterprise and the Claude Platform (API). In each product, an eligible admin can review the Busin
Anthropic Launches Claude for Teachers for US K-12 Educators
Anthropic's official account @claudeai has announced Claude for Teachers, offering free access to premium Claude capabilities for verified K-12 educators in the US. The program includes a library of teaching skills and a direct connection to evidence-based curricula mapped to academic standards in all 50 states.
Claude Code 2.1.209
- Fixed /model and other dialogs being blocked in `claude agents` background sessions (reverts an overly broad guard)
Claude Code 2.1.208
- Added screen reader mode: opt-in plain-text rendering for screen reader users. Run `claude --ax-screen-reader`, set CLAUDE_AX_SCREEN_READER=1, or add "axScreenReader": true to settings. - Added `vim
Anthropic Extends Claude Fable 5 Access and Claude Code's Higher Weekly Limits Through July 19
Anthropic has announced it is extending Claude Fable 5 access on all paid plans and keeping Claude Code's weekly rate limits 50% higher through July 19. The reasoning behind the extension and future plans were not included in the official announcement.
Claude Code 2.1.207
- Auto mode is now available without `CLAUDE_CODE_ENABLE_AUTO_MODE` opt-in on Bedrock, Vertex AI, and Foundry; disable via `disableAutoMode` in settings - Fixed the terminal freezing and keystrokes la
Anthropic Expands Claude for Open Source with 6 Months of Free Claude Max 20x
Anthropic's official account @ClaudeDevs announced an expansion of the Claude for Open Source program to more of the community. Eligible open source contributors can receive six months of Claude Max 20x at no cost. Applications are open starting today.
Anthropic Resets Usage Limits for All Users — 5-Hour and Weekly Counters Cleared
Anthropic's official developer account @ClaudeDevs announced on July 9 that 5-hour and weekly rate limits have been reset for all users. Here is what was cleared and what it means ahead of the Fable 5 deadline.