Artificial Intelligence1 min read

Show HN: Turbo-Browser-MCP – Batch forms, DOM deltas and submit guards for MCP

By · Published by Everything Blog

In short

The system introduces single-turn form prefilling across React, Shadow DOM, and iframes, as well as disk-based file uploads to avoid Base64 encoding overhead. In benchmark tests on headless Chromium, it reduced a 10-field form workflow from 11 turns and 72,614 cumulative tokens to a single 811-token exchange. It also features parallel tab sessions, network blocking presets, and automatic binary detection across major operating systems.

Key points

  • Consolidating browser actions into batched tools significantly reduces multi-turn model l…: Consolidating browser actions into batched tools significantly reduces multi-turn model latency and token overhead.
  • Critical operations are protected by default using a built-in human-in-the-loop submit gu…: Critical operations are protected by default using a built-in human-in-the-loop submit guard mechanism.
  • Flexible connection options support direct CDP, clean instances, and automatic detection…: Flexible connection options support direct CDP, clean instances, and automatic detection of existing signed-in browser sessions.

Sources checked by our analysis pipeline: 1

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

):

Capability | Typical Baseline | turbo-browser-mcp |

Speed / Turn Gain | Token Savings (o200k_base ) |

---|---|---|---|---|

Dense UI Snapshot (140-btn SaaS console) | 18,654 tok HTML / 3,568 tok full ARIA |

1,135 tok compact (28 ms ) |

1 call |

93.9% vs HTML (68.2% vs ARIA) |

Post-Click Delta Snapshot (onlyChanged: true ) |

3,582 tok full ARIA rescan |

56 tok changed lines (18 ms ) |

1 call |

98.4% vs ARIA (99.7% vs HTML) |

10-Field Complex Form + Snapshot (smart_fill_form ) |

11 turns (574 ms , 12,197 dir /…

Artificial Intelligence