Turbo-Browser-MCP - Token-efficient Playwright MCP server for browser automation
Show HN: Turbo-Browser-MCP – Batch forms, DOM deltas and submit guards for MCP
Turbo-Browser-MCP is a Playwright-based Model Context Protocol server that slashes LLM token waste and multi-turn latency in browser automation. It consolidates 25-33 granular browser primitives into just 10 batched tools, featuring delta DOM snapshots, single-turn React/Shadow DOM/iframe form filling, direct disk file uploads without Base64 in context, parallel tab sessions, network blocking presets, and a default human-in-the-loop submit guard. Benchmarks show a 10-field form filled in one turn instead of eleven (7x faster, 93.4% fewer tokens), a 48 KiB PDF upload using 99.8% fewer tokens, and post-click delta snapshots saving 98.4% versus full ARIA rescans.
Standard MCP servers charge an LLM round-trip for every snapshot, field fill, select choice, upload, and verification check. Turbo-Browser-MCP collapses all of that into batched calls with delta snapshots and inline verification, so your agent stops replaying history and starts actually getting things done.
- jonathanlydall
In addition to regular unit tests, we use Playwright to test our Electron app and also allow agents to drive our app using Playwright via MCP to validate their work or investigate bugs.
Based on past experience of the extreme fragility of testing against the DOM, I had Claude build an "automation API" for generally interacting with our app. Instead of LLMs needing to have Playwright click buttons or manually fill in forms or things like that, it instead executes scripts against a well defined API which we have our Angular "controllers" attach themselves to on "load" and then detach from on "unload".
So LLMs use pure JavaScript via the API and don't really need to use the DOM to interact with the app, but will do snapshots of the DOM as needed when investigating any bugs or visual issues.
This has worked very well for us, the API (like the rest of our app) is in TypeScript which means that we have a whole bunch static type safety automatically preventing regressions.
A gap in this approach is that the views themselves aren't really tested, we're e.g. testing that the logic called on pressing a button does all the right things like transition the system to new screens, etc, but not that the view is correctly bound to the button. In practice though, we've very rarely found situations where we wished we had automated testing the HTML of a view.
- lubujackson
Whoa, this looks incredible.
Having built my company's MCP server, I have a deeper appreciation for how important well-defined tools can be. It is clear to me that tool availability and coordination is going to be a top (or THE top) focus in the near future, more important than the model itself.
If you ever look at how an LLM greps through a codebase, pulling small slices at a time to gather what it needs, you have a sense of how precise tools can broaden a model's capabilities. If I had today's Sonnet with tooling from 5 years in the future, I expect it would beat Fable 5.2 hands down - that's how dramatic the difference is.
Anthropic/OpenAI have really buried the lede about tooling, baking it into their harnesses and trying to force lock-in. We are still in the AOL days of the internet right now.
- snake_doc
Hmm you should really benchmark against
https://github.com/browser-use/browser-harness
https://github.com/anomalyco/browse
https://github.com/vercel-labs/agent-browser
The answer is very likely not a MCP server. browse (anomalyco) is relatively new; but the other 2 are battle tested in production….