Claude Blog 采集 (2026-05-22)¶
共采集 5 篇文章
📋 文章索引¶
- New in Claude Managed Agents: self-hosted sandboxes and MCP tunnels - May 19, 2026 (评分: 9.0)
- Claude Security is now in public beta - Apr 30, 2026 (评分: 9.0)
- Updates to Claude Team - Jan 28, 2026 (评分: 9.0)
- Code w/ Claude SF 2026 recap: Building on the AI exponential - May 12, 2026 (评分: 9.0)
- Code with Claude comes to San Francisco, London, and Tokyo - Mar 18, 2026 (评分: 8.2)
New in Claude Managed Agents: self-hosted sandboxes and MCP tunnels¶
来源: Claude Blog 发布日期: May 19, 2026 采集时间: 2026-05-22 价值评分: 9.0/10 正文字数: ~2079 字符
摘要¶
Claude Managed Agents can now operate in a sandbox you control and connect to your private Model Context Protocol (MCP) servers
正文内容¶
Starting today, Claude Managed Agents can operate in a sandbox you control and connect to your private Model Context Protocol (MCP) servers. Both the sandbox where an agent executes tools and the services it reaches run within the established boundaries of your enterprise, under your security and runtime controls. The sandbox runs on your own infrastructure, or with managed providers like Cloudflare , Daytona , Modal , or Vercel to handle the compute and isolation for you. On the Claude Platform, self-hosted sandboxes is available in public beta and MCP tunnels in research preview ( request access ). Keep agent execution within your perimeter With self-hosted sandboxes, you keep sensitive files, packages, and services in your own infrastructure or with a managed sandbox provider. The agent loop that handles orchestration, context management, and error recovery stays on Anthropic’s infrastructure, while tool execution moves to your own configured environment. Inside your perimeter, network policies, audit logging, and security tooling are already in place, and files and repositories don't leave. You also control the compute: resource sizing and the runtime image are set on your side, so agents running compute-heavy work such as long builds or image generation get the CPU, memory, and capacity the task needs.
Getting started Both self-hosted sandboxes and MCP tunnels work within the same core primitives supported by Managed Agents. Self-hosted sandboxes is available in public beta and MCP tunnels in research preview. To get started with MCP tunnels, request access . Explore our docs to learn more, follow our cookbooks to set up your sandbox provider, or deploy your first agent in the Claude Console .
Explore more product news and best practices for teams building with Claude.
Transform how your organization operates with Claude
Product updates, how-tos, community spotlights, and more. Delivered monthly to your inbox.
Please provide your email address if you'd like to receive our monthly developer newsletter. You can unsubscribe at any time.
采集自 Claude Blog，由 collect_claude_blog.py 自动采集
Claude Security is now in public beta¶
来源: Claude Blog 发布日期: Apr 30, 2026 采集时间: 2026-05-22 价值评分: 9.0/10 正文字数: ~4140 字符
摘要¶
Scan code for vulnerabilities and generate proposed fixes with Opus 4.7, on the Claude Platform, or through technology and services partners building with Claude.
正文内容¶
Claude Security is now in public beta for Claude Enterprise customers. Scan code for vulnerabilities and generate proposed fixes with Opus 4.7, on the Claude Platform, or through technology and services partners building with Claude.
Claude Security is now available in public beta to Claude Enterprise customers. AI cybersecurity capabilities are advancing fast. Today’s models are already highly effective at finding flaws in software code; the next generation will be more capable still, and will be particularly effective at autonomously exploiting these flaws. Now is the time for organizations to act to improve their security, preparing for a world in which working software exploits are much easier to discover. Recently, we made Claude Mythos Preview—which can match or surpass even elite human experts at both finding and exploiting software vulnerabilities—available to a number of partners as part of Project Glasswing. But our cybersecurity efforts go beyond Glasswing: with Claude Security, a much wider set of organizations can put our most powerful generally-available model, Claude Opus 4.7, to work across their codebases. Opus 4.7 is among the strongest models available for finding and patching software vulnerabilities, and for discovering complex, context-dependent issues that might otherwise be missed. Claude Security—previously known as Claude Code Security—has already been tested by hundreds of organizations of all sizes in limited research preview, helping teams scan their codebases for vulnerabilities and generate targeted patches. Their feedback has shaped today’s release, which makes Claude Security available to all Enterprise customers. It comes with scheduled and targeted scans, easier integration with audit systems, and improved tracking of triaged findings. No API integration or custom agent build is required: if your organization uses Claude, you can start scanning today. Opus 4.7’s capabilities are also being brought to cyber defenders through Claude’s integration into software tools that many enterprises already use. Our technology partners, including CrowdStrike , Microsoft Security, Palo Alto Networks , SentinelOne , TrendAI , and Wiz are embedding Opus 4.7 into their tools; in addition, services partners like Accenture, BCG, Deloitte, Infosys and PwC are now helping organizations deploy Claude-integrated security solutions. We are entering a pivotal time for cybersecurity. AI is compressing the timeline between vulnerability discovery and exploitation. We believe the right response is to make sure defenders have access to frontier capabilities in the ways most accessible to them, through Claude directly and through our partners. How Claude Security works
We're still in the early days of AI-powered security. As our models improve and as we learn from the teams using Claude Security in production, we'll continue to expand what these tools can do. Meeting defenders where they work Claude Security is one part of our broader push to put frontier capabilities in defenders' hands. Much of its reach comes through the platforms and services partners teams rely on today. CrowdStrike , Microsoft Security, Palo Alto Networks , SentinelOne , TrendAI , and Wiz are integrating Opus 4.7’s capabilities into the security platforms that enterprises already run on today. Accenture, BCG, Deloitte, Infosys, and PwC are working alongside enterprise security organizations to deploy Claude-integrated security solutions for vulnerability management, secure code review, and incident response programs. Together, this means organizations can adopt these capabilities through whichever path fits how they already operate: directly in Claude Security, embedded in a platform they trust, or with a services team guiding the rollout.
Explore more product news and best practices for teams building with Claude.
Transform how your organization operates with Claude
Product updates, how-tos, community spotlights, and more. Delivered monthly to your inbox.
Please provide your email address if you'd like to receive our monthly developer newsletter. You can unsubscribe at any time.
采集自 Claude Blog，由 collect_claude_blog.py 自动采集
Updates to Claude Team¶
来源: Claude Blog 发布日期: Jan 28, 2026 采集时间: 2026-05-22 价值评分: 9.0/10 正文字数: ~1500 字符
摘要¶
We're making the Claude Team plan more accessible for growing teams. We’re lowering prices and introducing an annual discount for premium seats.
正文内容¶
Today, we're making the Claude Team plan more accessible for growing teams. We’re lowering prices and introducing an annual discount for premium seats. Lower pricing Standard seats are now $20 per month with annual discount, or $25 per month billed monthly Premium seats are now $100 per month with a new annual discount, or $125 per month billed monthly Every Team seat includes more usage than the Pro plan, and premium seats include five times the usage of standard seats. If power users need even more, admins can purchase additional capacity for their team. Built for how teams work The Team plan gives your teammates a shared workspace where everyone can collaborate with Claude on projects and access internal knowledge through connectors. Claude Code is included with every seat—whether you're a developer shipping features or a product manager automating workflows. Centralized admin controls and billing make it easy to manage your team. Your data stays private—we don't train Claude on your content by default. Getting started These changes are available now. Get started with the Team plan and visit our Help Center for more information.
Explore more product news and best practices for teams building with Claude.
Transform how your organization operates with Claude
Product updates, how-tos, community spotlights, and more. Delivered monthly to your inbox.
Please provide your email address if you'd like to receive our monthly developer newsletter. You can unsubscribe at any time.
采集自 Claude Blog，由 collect_claude_blog.py 自动采集
Code w/ Claude SF 2026 recap: Building on the AI exponential¶
来源: Claude Blog 发布日期: May 12, 2026 采集时间: 2026-05-22 价值评分: 9.0/10 正文字数: ~1135 字符
摘要¶
Check out our Code w/ Claude SF 2026 recap and product announcements, and watch the keynotes and sessions on YouTube.
正文内容¶
Missed our SF Code w/ Claude developer conference? Keynotes and breakout sessions are now on YouTube.
This week in San Francisco, we hosted Code w/ Claude , our annual developer conference. The event brought together developers, engineers, and founders for two days of keynotes, breakout sessions, and workshops with the teams building Claude. From prompting and model selection to architecting skills and scaling AI-native engineering teams , every session circled the same shift: the distance between an idea and production software is narrowing, and the teams getting the most leverage are designing for the AI exponential—not reacting to it. We demonstrated this through live coding sessions , customer deep-dives , and hands-on tutorials highlighting what this looks like today.
Explore more product news and best practices for teams building with Claude.
Transform how your organization operates with Claude
Product updates, how-tos, community spotlights, and more. Delivered monthly to your inbox.
Please provide your email address if you'd like to receive our monthly developer newsletter. You can unsubscribe at any time.
采集自 Claude Blog，由 collect_claude_blog.py 自动采集
Code with Claude comes to San Francisco, London, and Tokyo¶
来源: Claude Blog 发布日期: Mar 18, 2026 采集时间: 2026-05-22 价值评分: 8.2/10 正文字数: ~1466 字符
摘要¶
Technical sessions, live demos of new capabilities, and office hours with Anthropic engineers—watch live or apply to attend.
正文内容¶
Technical sessions, live demos of new capabilities, and office hours with Anthropic engineers—watch live or apply to attend.
Anthropic’s developer conference, Code with Claude , expands to three cities this spring. After launching in San Francisco last year, we’re also bringing Code with Claude to London and Tokyo for the first time. It’s a full day built for developers and founders with live workshops, demos of the latest capabilities, and 1:1 office hours with the teams behind Claude. This year’s agenda includes an expanded lineup of technical sessions and talks from Anthropic engineers and developers at startups and enterprises shipping with Claude. Check back in early April for a preview of the full agenda. Dates San Francisco : May 6, 2026 London : May 19, 2026 Tokyo : June 10, 2026 In-person space is limited across all three cities. Applications open today, attendees will be selected by random drawing and applicants will be notified in early April. Livestream access as well as recordings of sessions will be available to all. Register for the livestream or apply for an in-person seat here .
Explore more product news and best practices for teams building with Claude.
Transform how your organization operates with Claude
Product updates, how-tos, community spotlights, and more. Delivered monthly to your inbox.
Please provide your email address if you'd like to receive our monthly developer newsletter. You can unsubscribe at any time.
采集自 Claude Blog，由 collect_claude_blog.py 自动采集