jev-browser — security grade SAFE, quality 71/100

Security audit verdict: SAFE · quality 71/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by Ying-Kai-Liao · MCP Server · ★ 94

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is jev-browser safe to install? View the security audit →

About jev-browser

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 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. https://github.com/user-attachments/assets/2e688df9-4985-4854-8ebe-ba97c9d13d68 Jev only answers with probability distributions: yes/no (noul

browser-automationllm-agentsmcpmcp-serverplaywright

Quick Facts

Stars94
Forks16
LanguageJavaScript
CategoryMCP Server
LicenseMIT
Quality Score71.1087860376346/100
Last Updated2026-10-02
Created2026-09-16
Platformsbrowser, cli, mcp, node
Est. Tokens~15k

Compatible Skills

These tools work well together with jev-browser for enhanced workflows:

  • moltbrowser — semantic(0.23)+complementary+shared_fw(playwright)+same_lang+similar_pop+shared_platform (66%)

jev-browser alternative? Top 6 similar tools

Looking for a jev-browser alternative? If you're comparing jev-browser with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • apitap by n1byn1kt · ⭐ 126

    CLI, MCP server, and npm library that turns any website into an API — no docs, no SDK, no browser.

  • bitbucket-mcp by MatanYemini · ⭐ 165

    Bitbucket MCP - A Model Context Protocol (MCP) server for integrating with Bitbucket Cloud and Server APIs

  • camofox-mcp by redf0x1 · ⭐ 99

    Anti-detection browser MCP server for AI agents — navigate, interact, and automate the web without getting blo

  • g-search-mcp by jae-jae · ⭐ 273

    A powerful MCP server for Google search that enables parallel searching with multiple keywords simultaneously.

  • playwright-mcp by cloudflare · ⭐ 257

    Playwright MCP fork that works with Cloudflare Browser Rendering

  • langchainjs-mcp-adapters by langchain-ai · ⭐ 248

    ** THIS REPO HAS MOVED TO https://github.com/langchain-ai/langchainjs/tree/main/libs/langchain-mcp-adapters **

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular JavaScript Agent Tools

Frequently Asked Questions

What is jev-browser?

jev-browser is Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.. It is categorized as a MCP Server with 94 GitHub stars.

What programming language is jev-browser written in?

jev-browser is primarily written in JavaScript. It covers topics such as browser-automation, llm-agents, mcp.

How do I install or use jev-browser?

You can find installation instructions and usage details in the jev-browser GitHub repository at github.com/Ying-Kai-Liao/jev-browser. The project has 94 stars and 16 forks, indicating an active community.

What license does jev-browser use?

jev-browser is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to jev-browser?

The top alternatives to jev-browser on Agent Skills Hub include apitap, bitbucket-mcp, camofox-mcp. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools