Show HN: Turbo-Browser-MCP – Batch forms, DOM deltas and submit guards for MCP A developer released turbo-browser-mcp, a Playwright-based Model Context Protocol server that consolidates 25-33 fine-grained browser primitives into 10 batched tools to cut token use and multi-turn latency in LLM browser automation. Benchmarks run in headless Chromium with OpenAI o200k_base tokenization (tiktoken 0.14.0) show a dense 140-button UI snapshot at 1,135 tokens versus 18,654 for HTML (93.9% savings), a 10-field form completed in 1 turn at 811 tokens versus 11 turns and 12,197 direct tokens (7x faster, 93.4% direct savings), and a 48 KiB PDF upload at 85 tokens versus 44,728 tokens inline Base64 (99.8% saved). The server ships delta DOM snapshots, single-turn React/Shadow DOM/iframe form prefill, disk-path file uploads, parallel tab sessions, network blocking presets and a default human-in-the-loop Submit guard. 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 https://github.com/Tthanh2k6/turbo-browser-mcp/blob/main/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 / 72,614 cum tok | 1 turn 82 ms , 811 tok | 7x faster , 11 - 1 turns | 93.4% direct / 98.9% cumulative | | 48 KiB PDF Upload 49,152 bytes | 44,728 tok inline Base64 tool arg | 85 tok disk path 68 ms | Zero Base64 generation | 99.8% saved | | 6-Step Interactive UI Flow batch actions | 6 turns 411 ms , 955 dir / 3,162 cum tok | 1 turn 357 ms , 406 tok | 1.15x faster , 6 - 1 turns | 57.5% direct / 87.2% cumulative | | Open 6 Tabs Concurrently open many | 6 turns sequential 998 ms | 1 turn batched 420 ms | 2.38x faster , 6x fewer turns | 5 fewer prompt replays | | Heavy Media Load preset: "turbo" , 304 KiB assets | 252 ms , 9 media requests 304 KiB | 165 ms , 0 media requests 0 KiB | 1.53x faster | 100% media bandwidth cut | | Article Markdown Scraping extract clean text | 3,595 tok raw HTML 10,844 chars | 156 tok clean Markdown 641 chars | Clean reader output | 95.7% saved | | Diagnostics Triage page diagnostics errors-only | 3,460 tok unfiltered 32 req / 26 console | 601 tok default errors 2 req / 6 console | Zero noise scrolling | 82.6% saved | | Static MCP Tool Schema every turn overhead | 3,917 tok Playwright / 6,737 tok DevTools | 3,010 tok stripped 3,314 full w/ annotations | 10 tools vs 25 / 33 | 23.2% vs Playwright / 55.3% vs DevTools | 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. Standard MCP servers charge an LLM round-trip for every snapshot, field fill,