Show HN: Turbo-Browser-MCP – Batch forms, DOM deltas and submit guards for MCP
Turbo-Browser-MCP is a Playwright-based server designed to optimize browser automation for LLMs by batching tools and reducing token usage. It significantly lowers latency and costs by minimizing the number of LLM inference turns required for complex browser tasks.
Why it matters
It provides a practical solution to the high cost and latency issues currently hindering the efficiency of AI-driven browser agents.
turbo-browser-mcp is a Playwright-based Model Context Protocol (MCP) server built to cut LLM token waste and multi-turn latency in browser automation. It consolidates 25-33 fine-grained browser primitives into 10 batched tools featuring delta DOM snapshots, single-turn React/Shadow DOM/iframe form prefill, direct disk file uploads (no Base64 in context), parallel tab sessions, network blocking presets, and a default human-in-the-loop Submit guard.
All figures below come from benchmarks/benchmark.mjs ( npm run benchmark ) running headless Chromium locally with exact OpenAI o200k_base tokenization ( tiktoken 0.14.0 ):
Note on latency vs LLM inference turns: Eliminating 10 round-trips on a 10-field form saves both 7x in browser execution ( 574 ms -> 82 ms ) and 10 separate LLM inference round-trips ( 2-5s per turn in agent loops) plus ~71,800 replayed history tokens.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in