Claude Code v2.1.186: MCP CLI Auth, Bash Auto-Reply, and 20+ Fixes

Claude Code v2.1.186 ships with a batch of practical improvements: MCP server authentication from the CLI, automatic responses to bash commands, and over 20 bug fixes spanning session persistence, subagent management, and UI polish.
CLI Authentication for MCP Servers
Two new commands let you authenticate MCP servers without dropping into the interactive /mcp menu:
claude mcp login <name>claude mcp logout <name>
For SSH sessions, pass --no-browser and redirect stdin to complete the flow headlessly.
Bash Commands Now Auto-Reply
By default, ! bash commands now trigger Claude to automatically respond to the output—no more silent execution. To keep the previous behavior (bash output only added to context without a response), set "respondToBashCommands": false in settings.json.
Workflows & Subagents
- Press
fin the/workflowsagent detail view to filter by status. - Background subagents now surface permission prompts in the main session instead of auto-denying. The dialog shows which agent is asking; Esc denies just that tool.
Agent(type)deny rules andAgent(x,y)allowed-types restrictions now actually enforce for named subagent spawns.Workflow agent({schema})subagents will abort after 5 repeated schema validation failures instead of looping forever.- Teammates spawned via tmux/pane backends now inherit the leader's
--effortlevel.
Memory & Skills
- The agent is now reminded to compact its
MEMORY.mdindex when nearing the size limit. - Skill frontmatter keys (
display-name,default-enabled,fallback,metadata.*) now accept kebab-case, snake_case, and camelCase. - Malformed
SKILL.mdYAML frontmatter loads the skill body with empty metadata instead of failing silently.
Settings & Integrations
- Added
teammateMode: "iterm2"setting; warns when auto mode cannot find theit2CLI. - Added "Claude Platform on AWS - refresh credentials" option to
/loginwhenawsAuthRefreshis configured. CLAUDE_CODE_MAX_RETRIESnow caps at 15; for unattended sessions, useCLAUDE_CODE_RETRY_WATCHDOG./review <pr>now uses the same review engine as/code-review medium.
Bug Fixes (20+)
Notable fixes include streaming resuming after sleep (no more "Content block not found" or JSON parse errors), Chrome tab-group isolation applying correctly when the permissions gate is off for concurrent CLI sessions, background session recaps no longer duplicated, and ~~strikethrough~~ actually rendering as strikethrough instead of literal tildes. Also fixed: ESC/Ctrl+C responsiveness while background agents run, session cost now showing for usage-based Enterprise and Team subscribers, and a dark-theme flash when opening a background session from claude agents in a light terminal.
For the full changelog, see the source.
📖 Read the full source: GitHub Claude-Code
👀 See Also

LibreOffice Online Development Resumes After Community Vote
The Document Foundation has resumed work on LibreOffice Online after a community vote nullified the 2022 freeze. TDF will reopen the repository for contributions but won't host servers—instead providing self-hostable tools.

Claude CLI Directive Drift Issue Reported by Developer
A developer reports Claude CLI consistently ignores project directives stored in .claude folder files, particularly after auto-compact operations. The tool runs prohibited background processes and deletes task/session data despite explicit instructions.

Agentic Web Index: AI Bot Traffic Stats Show Mass Scraping, Spoofing
Known Agents' new index reveals bots make up 35% of web traffic, AI-related bot traffic grew 12%, and attackers are spoofing AI agents like ClaudeBot to run mass vulnerability scans.
Claude Code 2.1.233: GitLab MR support, memory limits, and security fixes
Claude Code v2.1.233 adds GitLab merge request URLs, opt-in memory limits for Bash, and fixes NTLM credential leak and CPU spin.