CClaude Code Docs, Rearranged
Docs / whats-new/2026-w26

Week 26 · June 22–26, 2026

Official documentation· View original ↗ ·Official text, no machine translation

Authenticate MCP servers from your shell with claude mcp login, get a response to shell mode command output with the ! prefix, and resume a conversation from before /clear with /rewind.

Releases v2.1.185 → v2.1.193 2 features · June 22–26
Authenticate MCP servers from the CLI v2.1.186

New `claude mcp login ` and `claude mcp logout ` commands authenticate a configured MCP server from your shell instead of the interactive /mcp menu. `claude mcp login` runs the server's OAuth flow directly, and `claude mcp logout` clears the stored credentials.

Run the OAuth flow for a configured server without opening a session:

claude mcp login sentry

Authenticate from the command line

Shell mode responds to command output v2.1.186

Commands you run with the ! prefix now get a response from Claude once the output lands in the transcript, so you can run ! npm test and get an explanation of the failures without a second prompt. The response costs the same as sending a normal prompt. To keep the earlier behavior, where the output is added to context without a response, set respondToBashCommands to false in settings.json.

Run a command and get a response to its output:

> ! npm test

Shell mode with the ! prefix

Other wins

/rewind can now resume a conversation from before /clear was run
New sandbox.credentials setting blocks sandboxed commands from reading credential files and secret environment variables
Org-configured model restrictions now apply to the model picker, `--model`, /model, and ANTHROPIC\_MODEL, with a "restricted by your organization's settings" message when a restricted model is selected
New autoMode.classifyAllShell setting routes all Bash and PowerShell commands through the auto-mode classifier, and denial reasons now show in the transcript, the denial toast, and /permissions
New claude\_code.assistant\_response OpenTelemetry log event carries the model's response text; deployments that already log prompt content start receiving it on upgrade, so set OTEL\_LOG\_ASSISTANT\_RESPONSES=0 to keep prompts only
Background subagents now surface permission prompts in the main session instead of auto-denying; the dialog shows which agent is asking, and Esc denies only that tool
/install-github-app can now install only the GitHub App and skip the Actions workflow and secret steps
Hosts you allow in the sandbox network permission dialog are remembered for the rest of the session instead of re-prompting on every connection
Streaming responses use about 37% less CPU, and long-session memory growth from the terminal output cache is reduced
`/review ` now uses the same review engine as /code-review medium
Bash mode ! commands get live file path autocomplete

Full changelog for v2.1.185–v2.1.193 →