vercel/vercel-plugin

Comprehensive Vercel ecosystem plugin — relational knowledge graph, skills for every major product, specialized agents, and Vercel conventions. Turns any AI agent into a Vercel expert.

What it solves

This plugin provides AI coding agents (like Claude Code, Cursor, and GitHub Copilot) with deep, structured knowledge of the Vercel ecosystem. It bridges the gap between a general-purpose AI agent and the specific workflows, APIs, and product relationships within Vercel, allowing agents to better assist with deployment, infrastructure management, and AI application development.

How it works

The plugin integrates into AI agent harnesses via a skill library and a relational knowledge graph. It uses a bundled .mcp.json to connect to Vercel's Model Context Protocol (MCP) server, enabling agents to read and write data (such as inspecting logs or creating deployments) directly. It also includes a library of 33 specialized skills and three expert agents (Deployment, Performance, and AI Architect) that can be invoked via slash commands or automatically injected into the agent's context based on theon project type.

Who it’s for

Developers using AI-powered IDEs or CLI agents who deploy their projects to Vercel, specifically those working with Next.js or the eve framework.

Highlights

  • Vercel MCP Connection: Enables agents to perform real-world actions like updating resources and creating deployments.
  • Relational Knowledge Graph: A text-form graph (vercel.md) that helps agents understand product relationships and decision matrices.
  • Extensive Skill Library: 33 specialized skills covering everything from AI SDK and AI Gateway to CDN caching and firewall management.
  • Broad Tool Support: Compatible with Claude Code, Cursor, GitHub Copilot CLI, OpenAI Codex, Grok Build, Kimi Code, and OpenCode 2.

Related

  • Project
    robzilla1738/harness-terminal

    A native macOS terminal with GPU acceleration and session persistence that integrates with AI coding agents to notify users when they need attention.

  • Project
    opalinehq/cli

    A CLI tool that syncs local Claude Code and Codex sessions to a shared workspace for team analytics and session visibility.

  • Project
    DaoyuanLi2816/mini-verl

    A single-GPU implementation of verl that enables running PPO, GRPO, and on-policy distillation on consumer NVIDIA GPUs.

  • Project
    Mengqi97/chinese-medical-dataset

    A curated collection of open-source Chinese medical datasets for tasks like medical QA, entity recognition, and knowledge graph construction to support the development of medical AI.