Reviews a system prompt against prompt engineering best practices — role framing, XML structure, few-shot quality, chain-of-thought justification, prompt injection defense, caching correctness, model-routing compatibility, and current API compatibility. Use when explicitly asked to review, audit, or check a system…
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.
Claude Code instructions for vijayanan6/mcp-project, covering claude.md, folder structure, commands, install all dependencies and open: http://localhost:8000.