---
title: "Comment by Mihai_LeanZero on \"Jev Ultrafast MCP: an autonomous browser for Claude Code\" | Hashnode"
description: "We run something adjacent for this exact kind of job -- scripted browser actions (Playwright launch plus saved storage state) for platform engagement, no LLM pe"
url: "https://hashnode.com/posts/jev-ultrafast-mcp-an-autonomous-browser-for-claude-code/6ab11425821f3934cde67d1b/comment/6ab1320e45de67de39ff9255"
---

[Discussion](https://hashnode.com/posts/jev-ultrafast-mcp-an-autonomous-browser-for-claude-code/6ab11425821f3934cde67d1b)

Comment [Jev Ultrafast MCP: an autonomous browser for Claude Code](https://hashnode.com/posts/jev-ultrafast-mcp-an-autonomous-browser-for-claude-code/6ab11425821f3934cde67d1b)

[Mihai\_LeanZero](https://hashnode.com/@mihaileanzero)

[Sep 21](https://hashnode.com/posts/jev-ultrafast-mcp-an-autonomous-browser-for-claude-code/6ab11425821f3934cde67d1b/comment/6ab1320e45de67de39ff9255)

We run something adjacent for this exact kind of job -- scripted browser actions (Playwright launch plus saved storage state) for platform engagement, no LLM per click, so the marginal token cost of a run is basically zero once the script exists. The interesting tradeoff your numbers surface is between that (zero marginal cost, but someone has to hand-write and maintain a script per site) and Jev's approach (goal-only calls, no per-site script, but you pay the decision model on every run). Curious how the decision-model cost compares once you factor in the manual-fallback re-runs after a captcha or blocking modal, since that's exactly the case where a hand-written script doesn't degrade at all.