---
title: "Discussion on \"Jev Ultrafast MCP: an autonomous browser for Claude Code\" | Hashnode"
description: "Discussion on \"Jev Ultrafast MCP: an autonomous browser for Claude Code\". I use Claude Code with two browser MCP servers: Claude in Chrome and Jev Ultrafast MCP. Both let Claude control a browser, but the approach is radically different. Claude in Chrome sends each click an"
url: "https://hashnode.com/posts/jev-ultrafast-mcp-an-autonomous-browser-for-claude-code/6ab11425821f3934cde67d1b"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Jev Ultrafast MCP: an autonomous browser for Claude Code](https://thomastartrau.hashnode.dev/jev-ultrafast-mcp-an-autonomous-browser-for-claude-code?utm_source=hashnode&utm_medium=feed)

I use Claude Code with two browser MCP servers: Claude in Chrome and Jev Ultrafast MCP. Both let Claude control a browser, but the approach is radically different. Claude in Chrome sends each click an

Sep 21 · 8 min read · thomastartrau.hashnode.dev  
Read the article

-   [#mcp](https://hashnode.com/tag/mcp)
-   [#claude-code](https://hashnode.com/tag/claude-code)
-   [#automation](https://hashnode.com/tag/automation)
-   [#productivity](https://hashnode.com/tag/productivity)

## Written by

[Thomas Tartrau](https://hashnode.com/@thomastartrau)

@thomastartrau · Paris, France

  
[View profile](https://hashnode.com/@thomastartrau)

## Responses 1

Markdown supported · ⌘↵ to post

[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.