CLI over MCP: a small Chrome DevTools experiment in Copilot CLI
7.4 relevance
Score Breakdown
technical depth 8
novelty 7
actionability 9
community 4
strategic 5
personal 9
Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.
Direct experiment comparing CLI vs MCP for browser tasks, highly actionable.
Summary
In Copilot CLI with gpt-5.3-codex-medium, wrapping Chrome DevTools MCP as a CLI skill via mcp2cli cut upfront context by ~5k tokens compared to direct MCP, avoiding schema-based discovery overhead. The CLI approach forces agent to learn tools through standard help mechanisms, reducing system prompt pollution and aligning with mcp2cli's claimed 96-99% token savings per turn. The experiment used a 9-step browser smoke test on a Python/Streamlit app, highlighting context bloat tradeoffs in agent frameworks.