MCP App StoreThe latest from the AI and MCP ecosystem, curated daily.
Sources
Anthropic launches Claude Managed Agents, enabling developers to deploy and scale reliable agents in production environments. The update focuses on stabilizing agentic workflows for enterprise use cases.
Claude Managed Agents now support scheduled execution and secure environment variable storage via vaults. This allows for automated background tasks and safer integration with authenticated CLI tools.
New observability tools for MCP server developers to monitor performance, diagnose latency, and submit servers to the directory in-app. The public beta is now live.
Anthropic releases a Swift package connecting Apple's Foundation Models framework to Claude. It enables developers to offload complex reasoning from on-device models to Claude with typed Swift outputs.
Anthropic releases the official product guide for Claude Cowork. The guide covers initial setup and best practices for deploying AI agents to handle complex professional tasks.
.jpg)
A case study on how Claude Code is used internally at Anthropic to automate GTM engineering tasks. It demonstrates significant time savings on repetitive research and email workflows.
Anthropic shares how the Claude Code team restructured their engineering processes to make agentic coding the default workflow. It provides a blueprint for scaling AI-native development practices in a professional engineering organization.
Anthropic shares strategies for using Claude to drive self-service data insights. The post highlights practical approaches to maximizing the model's analytical capabilities for data-driven decision making.
A deep dive into how Anthropic built and scaled hundreds of internal skills for Claude Code. It provides valuable lessons on agentic tooling and the architecture of specialized capabilities.
Anthropic provides a guide on effectively using Claude Cowork compared to Claude Code or standard chat. It focuses on workflow delegation and concrete steps for integrating agentic collaboration into development.
Claude Code now supports dynamic multi-agent harnesses, allowing it to orchestrate complex workflows on the fly. This enables more robust task execution through specialized, temporary agent structures.
Claude Code now supports dynamic workflows, enabling the execution of dozens to hundreds of parallel subagents for complex tasks. Includes built-in verification steps to ensure accuracy before delivering results.
CodeRabbit implements a structured planning layer on top of Claude to orchestrate coding agents. This approach allows teams to review and refine a coding plan before any actual code is generated, increasing reliability in complex agentic workflows.
Anthropic introduces a Zero Trust framework for enterprise AI agent deployment. It features a tiered architecture and an eight-phase workflow to mitigate autonomous agent threats and enable agentic SOAR.
.jpg)
Anthropic shares a framework for using Claude Opus to conduct threat modeling and vulnerability discovery. The approach focuses on iteratively identifying, triaging, and patching security flaws in source code.
.jpg)
Recap of the Code w/ Claude event in London, exploring new paradigms for AI-assisted development. Highlights shifts in developer workflows and the evolving relationship between humans and coding agents.
Anthropic has introduced new integrations with security and compliance tools, allowing IT teams to govern Claude across their entire stack. This improves enterprise deployment and security auditing for AI applications.
The Claude Code team explores using HTML instead of Markdown for agent outputs to create richer, more shareable, and readable content. A practical look at optimizing how AI coding tools present information to developers.
Anthropic's Head of US Mid-Market GTM demonstrates using Claude Cowork to automate customer briefs and territory scoring. The agentic workflow replaces hundreds of hours of manual cross-functional team effort.
.png)
Claude Managed Agents now support user-controlled sandboxes and direct connection to private MCP servers. This update significantly enhances security and extensibility for developers building custom agent integrations.