Claude Code v2.1.186: MCP CLI Auth, Workflow Enhancements and Numerous Fixes
Score
66Why selected
The new CLI MCP auth and automatic bash response features are highly practical, numerous bug fixes improve user experience, though some improvements are incremental; overall a significant update.
AI commentary
「This update significantly enhances Claude Code's CLI automation and stability, especially the introduction of MCP remote authentication and automatic bash response, enabling developers to use AI agents more efficiently in headless or SSH environments.」
Quick overview
Claude Code v2.1.186 introduces several new features and improvements. Added `claude mcp login/logout` commands to authenticate MCP servers from the CLI without opening the interactive menu, with --no-browser stdin redirect support for SSH. Workflow agent detail view now includes status filtering (press f), and the Plugin Installed tab has a new 'Skills' section. Bash commands now automatically trigger Claude to respond to output, configurable via settings. Fixed numerous issues including streaming request failures after wake from sleep, subagent transcript scroll position bleeding, duplicate background session recaps, Chrome tab-group isolation not applying, and many more. Improvements include MCP server name suggestions, memory compaction reminders for MEMORY.md, and multi-format support for skill frontmatter keys.
- New `claude mcp login/logout` CLI commands with --no-browser stdin redirect for SSH MCP server authentication
- Workflow agent detail view adds status filtering (press f), Plugin Installed tab adds 'Skills' section
- Bash commands now automatically trigger Claude to respond to output (configurable via settings)
- Fixed streaming request failures after sleep/wake, subagent scroll bleeding, duplicate recaps, and many other issues
Full text
Showing the source text; the full translation is being generated.
Uh oh!
There was an error while loading. Please reload this page.
anthropics / claude-code Public- Notifications You must be signed in to change notification settings
- Fork 21.9k
- Star 136k
v2.1.186
CompareChoose a tag to compare
Sorry, something went wrong.
Filter LoadingSorry, something went wrong.
Uh oh!
There was an error while loading. Please reload this page.
No results found
View all tags1228199
What's changed
- Added
claude mcp login <name>andclaude mcp logout <name>to authenticate MCP servers from the CLI without opening the interactive/mcpmenu, with--no-browserstdin redirect support for completing over SSH - Added status filtering (press
f) to the/workflowsagent detail view - Added a "Skills" section to the
/pluginInstalled tab - Added
teammateMode: "iterm2"setting with a warning when auto mode cannot find theit2CLI - Added "Claude Platform on AWS - refresh credentials" option to
/loginwhenawsAuthRefreshis configured !bash commands now trigger Claude to respond to the output automatically; set"respondToBashCommands": falsein settings.json to keep the previous context-only behavior- Fixed streaming requests failing with "Content block not found" or JSON parse errors after the machine wakes from sleep
- Fixed subagent transcript scroll position bleeding into the main transcript on exit
- Fixed background task previews flashing raw tool names before the agent's plan loaded
- Fixed Chrome tab-group isolation not applying when the in-product permissions gate is off for concurrent CLI sessions
- Fixed background session recaps being duplicated; the agent's own end-of-turn summary now shows as the recap line
- Fixed opening a background session from
claude agentsleaving the previous screen painted behind it - Fixed
Agent(type)deny rules andAgent(x,y)allowed-types restrictions not being enforced for named subagent spawns - Fixed Esc and Ctrl+C not responding while background agents are still running after the main turn ends
- Fixed misaligned option numbers in permission prompts when the option text overflows
- Fixed pressing
xon a finished subagent in the agent panel not dismissing it - Fixed a misleading "MCP server disconnected" notice for intentionally retired tools when resuming older sessions
- Fixed
/pluginInstalled showing a "more above" indicator when already scrolled to the top - Fixed
~~strikethrough~~showing literal tildes in assistant messages instead of rendering as strikethrough - Fixed
--toolsallowing feature-gated tools to slip through before flags loaded on a cold first launch - Fixed background job status in
claude agentsshowing a stale "needs input" message after replying - Fixed a dark-theme flash when opening a background session from
claude agentson a light terminal - Fixed mouse-selected text staying highlighted after deleting it in
claude agents - Fixed session cost not showing for usage-based Enterprise and Team subscribers
- Fixed agent teams: teammates spawned via tmux/pane backends now inherit the leader's
--effortlevel - Fixed Workflow
agent({schema})subagents looping forever on repeated schema validation failures instead of aborting after 5 attempts - Improved
claude mcp getandclaude mcp removeto suggest the closest configured server name on a typo and truncate long server lists - Improved memory: the agent is now reminded to compact its
MEMORY.mdindex when nearing the size limit - Improved skill frontmatter:
display-name,default-enabled,fallback, andmetadata.*keys now accept kebab-case, snake_case, and camelCase - Improved malformed
SKILL.mdYAML frontmatter handling: loads the skill body with empty metadata instead of failing silently - Changed
CLAUDE_CODE_MAX_RETRIESto cap at 15; for unattended sessions, useCLAUDE_CODE_RETRY_WATCHDOGinstead - Changed background subagents to surface permission prompts in the main session instead of auto-denying; the dialog shows which agent is asking, and Esc denies just that tool
- Changed
/review <pr>to use the same review engine as/code-review medium
Uh oh!
There was an error while loading. Please reload this page.
👍 4 saita08, Maaattqc, mike1858, and distinguished-sre reacted with thumbs up emoji 😄 2 saita08 and mike1858 reacted with laugh emoji 🎉 2 saita08 and mike1858 reacted with hooray emoji ❤️ 2 saita08 and mike1858 reacted with heart emoji 🚀 2 saita08 and mike1858 reacted with rocket emoji 👀 2 saita08 and mike1858 reacted with eyes emoji All reactions- 👍 4 reactions
- 😄 2 reactions
- 🎉 2 reactions
- ❤️ 2 reactions
- 🚀 2 reactions
- 👀 2 reactions
Related items
FeaturedDeepSeek V4 Doubles Token Share on OpenRouter, Driven by Agentic Workloads
DeepSeek V4 在 OpenRouter 上的代币份额翻倍,智能体工作负载成主要驱动力
The rapid adoption of DeepSeek V4 signals a strong market preference for high-performance, low-cost inference models, especially as agentic use cases reshape AI deployment.
91
FeaturedEnabling Two Settings Triples ARC-AGI-3 Benchmark Scores
启用两项设置使ARC-AGI-3基准测试分数提升三倍
This finding is crucial! It shows that model performance depends not only on training but also on inference-time configuration. For AI engineers and researchers, this is a must-know optimization direction. Teams deploying models on resource-constrained devices in particular could find a low-cost way to boost capabilities.
91
FeaturedGPT-5.6: Fusing Frontier Intelligence with Frontier Efficiency
GPT-5.6:前沿智能与前沿效率的融合
This news is worth watching as it marks a shift from pure parameter scaling to efficiency competition. For AI developers and business decision-makers, GPT-5.6 means higher performance at lower cost, especially for long-context or agentic tasks previously hindered by inference expenses. OpenAI's move may redefine what 'frontier' means.
91
FeaturedLFM2.5-Encoders: New Models for Fast Long-Context Inference on CPU
LFM2.5-Encoder:面向CPU快速长上下文推理的新模型
This blog post catches my eye because it directly solves the pain point of running long-context LLMs on CPU. For teams or individual developers without high-end GPUs, the LFM2.5-Encoder series offers a ready-to-use open-source solution. Highly recommended for those working on RAG, document search, or code analysis—now a standard server can handle million-token documents.
91
FeaturedGPT-Red: OpenAI Automates Red Teaming via Self-Play to Boost Model Robustness
GPT-Red:OpenAI通过自我对弈实现AI红队自动化,提升模型鲁棒性
GPT-Red marks a milestone from human to automated red-teaming—essential for safety engineers and alignment researchers. While reducing cost, it also raises ethical questions about automated attacks, worth pondering for everyone in AI governance.
91
FeaturedOpenAI Launches GPT-5.5 Bio Bug Bounty Program
OpenAI推出GPT-5.5生物漏洞赏金计划
This program deserves attention as it pioneers the extension of AI bug bounty to biosecurity, offering a new research direction for the security community and a practical training ground for AI risk governance. It is particularly important for model safety researchers, biosecurity experts, and practitioners concerned about dual-use AI risks.
91
FeaturedvLLM Introduces Native-Speed Transformers Modeling Backend for Enhanced Inference Performance
vLLM推出原生速度Transformers建模后端,大幅提升推理性能
This update is critical for AI engineering teams: eliminating format conversion speeds up model iteration, and 2-5x speedup directly reduces GPU costs. If you're building LLM online services or batch inference, this is practically a must-read technical update.
90
FeaturedGoogle DeepMind Introduces SL2T, a Sign Language-to-Text Model for Deaf Users
Google DeepMind 发布手语转文本模型 SL2T,助力聋人用户
This news matters not only as a technical breakthrough but also as a sign that AI is beginning to address the needs of marginalized groups. For developers, the architecture and technical approach of SL2T merit deep study; for accessibility advocates, it's a key case for advancing industry standards.