“vercel”

Platform for deploying apps and AI agents, with an AI Gateway, sandboxes and fluid compute.

Vercel CLI expert guidance.

Feature flags, A/B tests, and gradual rollouts with Vercel Flags, in any app or framework.

An MCP server for Vercel

Vercel Agent guidance — dashboard and Slack chat, code review, production investigation, approved actions, and product installation.

Vercel Firewall expert guidance — automatic DDoS mitigation, the Vercel WAF (custom rules, IP blocking, managed rulesets, rate limiting), Attack Mode, system…

TypeScript toolkit for AI apps and agents with a unified provider API, streaming, UI hooks and a wrapper for running established agent harnesses.

Configure and troubleshoot Vercel Services for multiple frontends and backends in one project.

Set up OpenTelemetry instrumentation for Vercel Tracing and query the resulting spans.

Vercel storage expert guidance — Blob, Global Config (formerly Edge Config), and Marketplace storage (Neon Postgres, Upstash Redis).

Vercel Connect expert guidance for securely obtaining scoped credentials for third-party services on behalf of apps or users.

Vercel Sandbox guidance — ephemeral Firecracker microVMs for running untrusted code safely.

Deploy and manage projects on Vercel using token-based authentication.

Isolated Linux microVMs for running agent-generated or untrusted code, driven by an SDK and CLI.

Vercel Functions expert guidance — Node.js/Bun/Python runtimes, Fluid Compute, long-duration (30 min) functions, large functions (5 GB bundles), Docker/OCI…

Makes ordinary TypeScript async functions durable, with suspend, resume and retries.

Vercel's agent that investigates production issues and reviews code, asking for approval before it takes actions.

Deploy applications and websites to Vercel.

Access and test Vercel deployments protected by Vercel Authentication, SSO, or Deployment Protection.

Deploy and manage projects on Vercel using token-based authentication.

React and Next.js performance optimization guidelines from Vercel Engineering.

Use when deploying an app or site to Vercel (preview or production).

Managed gateway with one API key for 400+ models across providers, with fallbacks and no token markup.

Run live eval sessions against the vercel-plugin to verify hook behavior, skill injection, dedup correctness, and coverage.