vercel

vercel-plugin

Getting Started

Supported Tools

Tool	Status
Claude Code	Supported
Cursor	Supported
GitHub Copilot CLI	Supported
OpenAI Codex	Supported
Grok Build	Supported
Kimi Code	Supported
OpenCode 2	Supported

Prerequisites

• One of the supported AI coding tools listed above
• Node.js 18+
• Bun

Installation

npx plugins add vercel/vercel-plugin

That's it. The plugin installs Vercel context, skills, and a lightweight default hook profile.

For OpenCode 2, install it as a native OpenCode plugin:

opencode plugin add github:vercel/vercel-plugin

OpenCode loads the same skills, agents, commands (/vercel:deploy, /vercel:env, /vercel:status, /vercel:bootstrap), session context, and Vercel MCP server. Run /mcps in OpenCode to sign in to the MCP server. Node.js and Bun are not needed for OpenCode.

What It Does

This plugin gives AI agents a relational knowledge graph of the Vercel ecosystem plus a bundled skill library covering products, libraries, CLI, APIs, and workflows.

How Do I Use This?

After installing, the plugin keeps automatic behavior lightweight. Session-start activation now only kicks in for empty directories and detected Vercel, Next.js, or eve projects, and Vercel skills are no longer auto-injected on every tool call or every prompt by default. The default post-tool path is now observer-only. The skills remain available for direct use, and the repo still keeps the injection engine for targeted or future opt-in workflows.

Vercel MCP connection

The bundled .mcp.json connects to https://mcp.vercel.com. Authenticate and grant access to the intended teams before using account tools. MCP supports both reads and writes, including inspecting projects and logs, creating deployments, and updating resources. Inspect the tools and schemas exposed by your connection. Domain registration requires a quote and explicit approval; digital subscriptions, credits, and add-on purchases are unavailable through MCP.

Components

Ecosystem Graph (vercel.md)

A text-form relational graph covering:

• All Vercel products and their relationships
• Decision matrices for choosing the right tool
• Common cross-product workflows
• Migration awareness for sunset products

Skills (34 skills)

Skill	Covers
access-protected-vercel-deployment	Authenticated CLI and browser access to protected preview and production deployments using vc curl, OIDC, and Trusted Sources
ai-gateway	Unified model API, provider routing, failover, cost tracking, 100+ models
ai-sdk	AI SDK 7 — text/object generation, streaming, tool calling, agents, MCP, providers, embeddings
auth	Authentication integrations — Clerk, Better Auth, Descope, Auth0 setup for Next.js with Marketplace provisioning
bootstrap	Project bootstrapping orchestrator — linking, env provisioning, db setup, first-run commands
build-agents	Default eve-first agent builder — create AI agents, agent apps, tools, channels, schedules, and Slack agents
cdn-caching	Diagnose cache hit rate, stale content, revalidation behavior, per-request cache reasons, and ISR read/write cost across CDN/ISR/PPR
chat-sdk	Multi-platform chat bots — Slack, Telegram, Teams, Discord, Google Chat, GitHub, Linear
create-a-backend	Backend product and framework selection — Functions, Services, containers, Workflow, Queues, and databases
custom-metrics	Emit numeric application and business measurements from Functions and query them with vc metrics
daemons	Vercel Daemons — long-running Dockerfile-built workers declared under daemons in vercel.json, instances per region, SIGTERM, Queues poll mode
deployments-cicd	Deployment and CI/CD — deploy, promote, rollback, --prebuilt, CI workflow files
domains	Public domain search and pricing, CLI and Registrar API operations, project domains, DNS, transfers, and renewals
env-vars	Environment variable management — .env files, vercel env commands, OIDC tokens
eve	Filesystem-first framework for durable AI agents, agent applications, channels, sandboxes, schedules, evals, and frontend clients
flags-sdk	Feature flags and A/B tests — Flags SDK, provider adapters, vercel flags CLI, precompute, Flags Explorer
is-agentic	Score how ready a website, domain, or public MCP endpoint is for AI agents, and act on the Is Agentic report
knowledge-update	Knowledge update guidance for the plugin
marketplace	Integration discovery and installation (vercel integration add / vercel install), provider agent skills, auto-provisioned env vars, unified billing
microfrontends	Multi-zone and microfrontend architecture, routing, deployment boundaries, and shared dependencies
queues	Vercel Queues — durable topics, @vercel/queue publish/consume, consumer groups, retries, delays, idempotency, Queues vs Workflows
react-best-practices	React/Next.js performance optimization — 64 rules across 8 categories
routing-middleware	Request interception before cache, rewrites, redirects, personalization — Edge/Node.js/Bun runtimes
runtime-cache	Ephemeral per-region key-value cache, tag-based invalidation, shared across Functions/Middleware/Builds
vercel-agent	Vercel Agent chat (dashboard, Slack), code review, investigations, approved actions, product installation
vercel-cli	All CLI commands — deploy, env, dev, domains, cache management, MCP integration, marketplace
vercel-connect	Managed OAuth tokens and third-party connections for apps, MCP servers, and eve agents
vercel-firewall	DDoS protection, WAF rules, rate limiting, bot filtering, and IP controls
vercel-functions	Node.js, Bun, Python, and Rust runtimes on Fluid Compute, streaming, WebSockets, Cron Jobs, configuration
vercel-sandbox	Ephemeral Firecracker microVMs for running untrusted/AI-generated code safely
vercel-services	Multiple frontends and backends in one project, with public rewrites and private service bindings
vercel-storage	Blob, Global Config (formerly Edge Config), Neon Postgres, Upstash Redis, migration from sunset packages
verification	Full-story verification — infers user story, verifies end-to-end browser → API → data → response
workflow	Workflow SDK — durable execution, WorkflowAgent, steps, Worlds, pause/resume

Next.js framework guidance comes from Next.js itself, following the official agent setup: version-matched docs bundled in node_modules/next/dist/docs/ (with AGENTS.md generated by next dev on 16.3+), plus workflow skills installed with npx skills add vercel/next.js. The plugin points agents there instead of shipping its own Next.js skills.

Agents (3 specialists)

Agent	Expertise
deployment-expert	CI/CD pipelines, deploy strategies, troubleshooting, environment variables
performance-optimizer	Core Web Vitals, rendering strategies, caching, asset optimization
ai-architect	AI application design, model selection, streaming architecture, MCP integration

Commands (4 commands)

Command	Purpose
/vercel-plugin:bootstrap	Bootstrap project — linking, env provisioning, db setup
/vercel-plugin:deploy	Deploy to Vercel (preview or production)
/vercel-plugin:env	Manage environment variables
/vercel-plugin:status	Project status overview

Hooks

Lifecycle hooks that run automatically during your session:

• Session start context injection — Injects a thin Vercel session context plus the knowledge-update guidance for empty directories and detected Vercel, Next.js, or eve projects
• Session start repo profiler — Scans config files and dependencies to set likely-skill hints, but only after that same activation check passes

Usage

After installing, session context is injected automatically only for empty directories and detected Vercel, Next.js, or eve projects. Vercel skills are available on demand, and you can invoke them directly via slash commands:

/vercel-plugin:build-agents
/vercel-plugin:ai-sdk
/vercel-plugin:deploy prod

Telemetry

Telemetry is on by default and can be disabled with VERCEL_PLUGIN_TELEMETRY=off.

What is collected:

• dau:active_today: sent at most once per UTC day when the plugin runs.
• plugin:first_use: sent once per local user profile the first time the plugin successfully reports telemetry.
• plugin:version: sent with telemetry batches so usage can be grouped by plugin version.
• plugin:install_id: the locally stored random installation UUID.
• plugin:agent_harness: each distinct detected agent harness category observed per installation per UTC day.
• skill:invoked: the name of a skill or command that ships with this plugin (for example ai-sdk, workflow, deploy) each time it is loaded through the agent's Skill tool — whether you typed the slash command or the model chose it. See Skill telemetry below.