Is the jev-browser MCP server actively maintained?

The jev-browser MCP server was last committed 1mo ago and has 3 contributors. Issue health: 0% of issues resolved. AgentRank freshness score reflects real-time maintenance activity.

jev-browser MCP Server

Name: Ying-Kai-Liao/jev-browser
Rating: 3.2 (1 reviews)
Author: Ying-Kai-Liao

Ying-Kai-Liao/jev-browser

Score: 55.8 Rank #8963 Agent Framework

[![AgentRank](https://agentrank-ai.com/api/v1/badge/Ying-Kai-Liao--jev-browser)](https://agentrank-ai.com/tool/Ying-Kai-Liao--jev-browser/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

Are you the maintainer of Ying-Kai-Liao/jev-browser? Claim this listing →

Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.

Add AgentRank to Claude Code Discover and compare tools like Ying-Kai-Liao/jev-browser — your AI finds the right one automatically

Get API Access →

claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

Ying-Kai-Liao/jev-browser is a JavaScript MCP server licensed under MIT. Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server. Topics: browser-automation, llm-agents, mcp, mcp-server, playwright.

Ranked #8963 out of 24846 indexed tools.

Ecosystem

JavaScript MIT

browser-automationllm-agentsmcpmcp-serverplaywright

Score Breakdown

Stars 15% 112

112 stars → growing community

Freshness 25% 1mo ago

Last commit 1mo ago → moderate activity

Issue Health 25% 0%

0/1 issues closed → many open issues

Contributors 10% 3

3 contributors → small team

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A

PyPI Downloads N/A

Forks 20

Description Good

License MIT

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

Freshness high impact

Last commit was 34 days ago — a recent commit would boost your freshness score

Issue Health high impact

You have 1 open vs 0 closed issues — triaging stale issues improves health

Badge all embed codes →

Markdown

[![AgentRank](https://agentrank-ai.com/api/v1/badge/Ying-Kai-Liao--jev-browser)](https://agentrank-ai.com/tool/Ying-Kai-Liao--jev-browser/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

HTML

<a href="https://agentrank-ai.com/tool/Ying-Kai-Liao--jev-browser/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/Ying-Kai-Liao--jev-browser" alt="AgentRank"></a>

Embed Widget docs →

HTML

<script src="https://agentrank-ai.com/embed.js" data-tool="Ying-Kai-Liao/jev-browser"></script>

Details

Stars: 112
Forks: 20
Open Issues: 1
Closed Issues: 0
Contributors: 3
Dependents: —
Language: JavaScript
License: MIT
Last Commit: 1mo ago

Matched Queries

"mcp server""mcp-server"topic:mcptopic:mcp-server

From the README

# jev-browser

Browser automation where an LLM plans and **Jev** decides.

> Unofficial project, not affiliated with TypeSafe. It calls the TypeSafe System One API
> with your own API key.

The calling LLM (Claude, via MCP) says what outcome it wants, one step at a time, and hands
over any text to type. For each round of a step, code describes the page. Then one ~300 ms
[Typesafe System One](https://docs.typesafe.ai) request asks Jev several questions at once:
which element, which action, which value, and is the step done / blocked / showing an error /
about to do something irreversible. Playwright performs the action. The LLM never reads page
snapshots unless it chooses to take over.

```
Claude ── browser_do("Log in", {email, password}) ──▶ jev-browser
                                                       │  loop until done / stuck / needs confirmation
                                                       │   1. settle   (network + DOM quiet)

Read full README on GitHub →