The Nuxt MCP Toolkit officially supports 'MCP apps', allowing AI agents to render complete UIs instead of plain text, significantly enhancing the user experience.
The Vercel CLI has introduced the 'vercel curl' command, enabling developers to use standard curl syntax and automatically bypass Deployment Protection via CLI authentication.
Vercel has introduced price sorting and unregistered domain filtering, helping developers optimize budgets and save search time.
Vercel has announced it will stop charging for CDN and data transfer traffic blocked by its Web Application Firewall (WAF), protecting users from unexpected bill shocks during bot attacks.
Vercel Sandbox now allows running Claude Managed Agents in isolated Firecracker microVM environments, combining Anthropic's management capabilities with Vercel's secure infrastructure.
Vercel has officially launched Sandbox Persistence into General Availability (GA), enabling automatic data recovery between working sessions.
The Vercel CLI tool has introduced a new command, allowing developers to configure traffic splitting directly from the command line for feature testing.
Firecrawl has officially launched on the Vercel Marketplace, providing an optimized web scraping solution for LLMs without the hassle of managing complex crawling infrastructure.
Vercel updates its Microfrontends routing mechanism, supporting complete configuration inheritance when using aliases and enabling automatic Git branch-based routing across the entire system.
Vercel has added a new command to its CLI, allowing developers to quickly retrieve anomaly alerts alongside AI analysis directly from the terminal.
Vercel continuously integrates new AI models from xAI and Google alongside an automatic provider sorting feature to help developers optimize both cost and performance.
Vercel has introduced a new deployment list interface with a high-density layout, helping developers monitor project statuses more efficiently across all devices.
Vercel has released the AI Gateway plugin for WordPress 7.0, enabling connections to hundreds of AI models from more than 40 providers with just a single API key.
Vercel launches Flat Rate CDN (Beta) with a fixed monthly fee, helping Pro teams control costs regardless of traffic spikes.
Vercel has updated its AI Gateway with the ability to set a team-wide provider allowlist. This feature helps organizations tightly control data flow, ensuring only security-vetted vendors process requests.
Vercel has announced support for Claude Opus 4.8 on its AI Gateway, enabling developers to handle complex programming tasks and write more coherent text.
Vercel integrates Amazon OpenSearch Serverless directly into its Dashboard, enabling developers to set up vector search infrastructure for AI Agents with just a few clicks while cutting costs by up to 60%.
The experimental version of Vercel CLI now officially supports native binaries for Windows, macOS, and Linux, boosting startup speeds and eliminating dependency on the Node.js runtime.
Vercel has introduced OIDC authentication for Vercel Blob, enabling short-lived, automatically rotating tokens instead of long-lived credentials. This update enhances security and is now the default setting for new connections.
Vercel's build infrastructure now automatically detects and upgrades specs when memory limits are approached, preventing OOM failures through dynamic scaling.
Vercel has added official adapters for Lark and Feishu to its Chat SDK, enabling developers to build secure interactive bots without exposing webhook ports.
Vercel has updated its Chat SDK, deeply integrating the AI SDK toolkit and enabling direct access to SDKs of platforms like GitHub, Slack, and Linear to build AI agents.
Vercel's new feature simplifies pull request management for large monorepo projects by consolidating multiple commit statuses into one.
The latest update to the Vercel Chat SDK enables 'human-in-the-loop' workflow integration by sending payloads directly to endpoints when users interact with chat cards.
Conductor, a multi-agent IDE, has shifted its execution layer from local machines to the cloud using Vercel Sandbox. This solution enables engineering teams to run multiple AI coding agents in parallel without hardware limitations.
