--- title: Vercel Plugin for AI Coding Agents product: vercel url: /docs/agent-resources/vercel-plugin canonical_url: "https://vercel.com/docs/agent-resources/vercel-plugin" last_updated: 2026-07-29 type: reference prerequisites: - /docs/agent-resources related: [] summary: Install the Vercel plugin to give supported AI coding tools Vercel context, skills, specialist agents, slash commands, and lightweight session-start... install_vercel_plugin: npx plugins add vercel/vercel-plugin --- # Vercel Plugin for AI Coding Agents The Vercel plugin gives [supported AI coding tools](#supported-tools) Vercel-specific context, skills, agents, and slash commands. The default installation keeps automation lightweight and activates session-start context only in empty directories and detected Vercel, Next.js, or eve projects. ## Getting started ### Prerequisites - One of the [supported tools](#supported-tools) - Node.js 18 or later - [Bun](https://bun.sh) ### Installation ```bash npx plugins add vercel/vercel-plugin ``` The plugin installs Vercel context, skills, and a lightweight default hook profile. ### Install in OpenCode [OpenCode](https://opencode.ai) 2 uses its own plugin command and doesn't need Node.js or Bun: ```bash opencode plugin add github:vercel/vercel-plugin ``` To connect the Vercel MCP server, run `/mcps` in OpenCode, select **vercel**, and sign in. Slash commands use the `vercel:` prefix, such as `/vercel:deploy prod`. Run `opencode plugin update` to get new versions. ### Usage After installation, session context is injected automatically only for empty directories and detected Vercel, Next.js, or eve projects. You can invoke skills and commands directly when you want targeted guidance: ```text /vercel-plugin:build-agents /vercel-plugin:ai-sdk /vercel-plugin:deploy prod ``` ## What the plugin provides | Component | Description | | ----------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- | | **Ecosystem graph** | A relational knowledge graph covering every Vercel product, library, CLI, API, and service, with decision matrices and cross-product workflows | | **[33 skills](#available-skills)** | Deep-dive guidance for specific Vercel products, libraries, and workflows | | **3 specialist agents** | Purpose-built agents for deployment, performance optimization, and AI architecture | | **4 slash commands** | Quick actions for deploying, managing environment variables, bootstrapping projects, and more | ## Supported tools The plugin installs into these coding tools. Each tool has its own installation flow. | Tool | Status | | ------------------------------------------------------------------------------- | --------- | | [ChatGPT](https://chatgpt.com) | Supported | | [Claude Code](https://code.claude.com/docs) | Supported | | [Codex CLI](https://learn.chatgpt.com/docs/codex/cli) | Supported | | [Cursor](https://www.cursor.com) | Supported | | [GitHub Copilot](https://github.com/features/copilot) | Supported | | [GitHub Copilot CLI](https://github.com/github/copilot-cli) | Supported | | [Grok Build](https://x.ai/build) | Supported | | [Kimi Code CLI](https://github.com/MoonshotAI/kimi-code) | Supported | | [OpenCode](https://opencode.ai) 2 | Supported | | [VS Code](https://code.visualstudio.com) | Supported | ## How it works After installation, the plugin keeps automatic behavior lightweight. Session-start activation runs only in empty directories and detected Vercel, Next.js, or eve projects, and Vercel skills are not auto-injected on every prompt or every tool call by default. The skills remain available on demand, and the plugin includes the injection engine for targeted or future opt-in workflows. ### Default hooks - **Session start context injection**: Injects a thin Vercel session context plus `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 after the same activation check passes ## Available skills The plugin includes 33 skills covering the Vercel ecosystem: | Skill | Covers | | ------------------------------------ | ------ | | `access-protected-vercel-deployment` | Authenticated CLI and browser access to protected preview and production deployments with `vc curl`, OIDC, and Trusted Sources | | `ai-gateway` | Unified model API, provider routing, failover, cost tracking, and hundreds of models | | `ai-sdk` | AI SDK 7, including text and object generation, streaming, tool calling, agents, MCP, and embeddings | | `auth` | Authentication integrations for Clerk, Better Auth, Descope, and Auth0 with Marketplace provisioning | | `bootstrap` | Project bootstrapping, including linking, environment provisioning, database setup, and first-run tasks | | `build-agents` | Default guidance for building AI agents with eve, including tools, channels, schedules, and Slack agents | | `cdn-caching` | Cache hit rate, stale content, revalidation, per-request cache reasons, and ISR read and write costs | | `chat-sdk` | Multi-platform chat bots for Slack, Telegram, Teams, Discord, Google Chat, GitHub, and Linear | | `create-a-backend` | Choosing between Functions, Services, containers, Workflow, Queues, and databases for a backend | | `custom-metrics` | Application and business metrics emitted from Functions and queried with `vc metrics` | | `deployments-cicd` | Deployment and CI/CD workflows, including deploy, promote, rollback, `--prebuilt`, and CI files | | `domains` | Domain search and pricing, registration, project domains, DNS, transfers, and renewals | | `env-vars` | Environment variable management, including `.env` files, `vercel env`, and OIDC tokens | | `eve` | The eve framework for durable AI agents, including channels, sandboxes, schedules, evals, and frontend clients | | `flags-sdk` | Feature flags and A/B tests with the Flags SDK, provider adapters, the `vercel flags` CLI, and Flags Explorer | | `is-agentic` | Agent readiness scores for websites and public MCP endpoints with Is Agentic | | `knowledge-update` | Knowledge update guidance for the plugin | | `marketplace` | Integration discovery and installation with `vercel integration add` and `vercel install`, auto-provisioned environment variables, and unified billing | | `microfrontends` | Microfrontends on Vercel, including path routing, project composition, local development, and troubleshooting | | `queues` | Vercel Queues, including durable topics, consumer groups, retries, delays, and idempotency | | `react-best-practices` | React and Next.js performance guidance across component, data, and rendering patterns | | `routing-middleware` | Request interception before cache, rewrites, redirects, and personalization for Edge, Node.js, and Bun | | `runtime-cache` | Ephemeral per-region key-value cache with tag-based invalidation across Vercel Functions, Routing Middleware, and Builds | | `vercel-agent` | Vercel Agent in the dashboard and Slack, including code review, investigations, and approved actions | | `vercel-cli` | Vercel CLI commands for deploy, env, dev, domains, cache management, MCP integration, and Marketplace provisioning with `vercel install` | | `vercel-connect` | Vercel Connect guidance for scoped OAuth tokens, third-party services, MCP servers, and eve agent connections | | `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, and Cron Jobs | | `vercel-sandbox` | Ephemeral Firecracker microVMs for running untrusted or 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, Neon Postgres, Upstash Redis, one-command Marketplace provisioning with `vercel install`, and migration from sunset packages | | `verification` | End-to-end verification across browser, API, data, and response flows | | `workflow` | Workflow SDK, including durable execution, WorkflowAgent, steps, Worlds, and pause or resume flows | The plugin doesn't ship Next.js skills. Next.js includes version-matched docs for agents, and you can add its workflow skills with `npx skills add vercel/next.js`. See the [Next.js AI agents guide](https://nextjs.org/docs/app/guides/ai-agents). ## Specialist agents The plugin includes three specialist agents: | 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 | ## Slash commands Use slash commands directly in your AI coding tool: | Command | Purpose | | ---------------------------- | ----------------------------------------------------------------- | | `/vercel-plugin:bootstrap` | Bootstrap a project with linking, env provisioning, and db setup | | `/vercel-plugin:deploy` | Deploy to Vercel (preview or production) | | `/vercel-plugin:env` | Manage environment variables (list, pull, add, remove, diff) | | `/vercel-plugin:status` | View project status, recent deployments, and environment overview | To deploy to production, pass `prod` as an argument: ```text /vercel-plugin:deploy prod ``` ## Telemetry Prompt text and bash and tool-call telemetry are not collected. Telemetry behavior: - If `VERCEL_PLUGIN_TELEMETRY` is unset, the plugin sends a once-per-day `dau:active_today` event, and a `skill:invoked` event with the name of each plugin skill your agent loads - `VERCEL_PLUGIN_TELEMETRY=off` disables all telemetry, including both events To disable telemetry in shells that launch your AI coding tool: ```bash export VERCEL_PLUGIN_TELEMETRY=off ``` ```powershell setx VERCEL_PLUGIN_TELEMETRY off ``` ## Debugging If the plugin is not behaving as expected, enable debug logging with `VERCEL_PLUGIN_LOG_LEVEL`: ```bash export VERCEL_PLUGIN_LOG_LEVEL=debug ``` Available log levels: | Level | Description | | --------- | ------------------------------------------- | | `off` | No logging (default) | | `summary` | High-level injection summaries | | `debug` | Detailed matching and dedup information | | `trace` | Full pipeline traces with timing breakdowns | You can also run the built-in doctor command: ```bash npx vercel-plugin doctor ``` The doctor command validates manifest parity, checks hook timeout risk, verifies dedup health, and reports skill map issues. ## Reporting issues If a skill gives incorrect advice or injection does not fire when expected, file an issue on [GitHub](https://github.com/vercel/vercel-plugin/issues). Include: - What you were building - What the plugin injected, or did not inject. Enable debug logs with `VERCEL_PLUGIN_LOG_LEVEL=debug` - What was wrong about it --- [View full sitemap](/docs/sitemap)