Uni-CLI — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

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 olo-dot-io · MCP Server · ★ 270

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

🔒 Is Uni-CLI safe to install? View the security audit →

About Uni-CLI

Uni-CLI English · 简体中文 The universal computer-control platform for agents: an agent control plane for real software. Install once, search by intent, and run the smallest governed operation across websites, browsers, desktop apps, local tools, files, operating systems, and agent protocols. Browser automation, computer-use sandboxes, MCP servers, local code execution, accessibility, screenshots, app wrappers, and external CLIs are action substrates below one loop: intent in, governed action out, evidence back, repair or reroute until the result is delivered. Docs · Operation catalog · Agent index <img alt="Node 22.19+" src="https://img.shields.io/badge/node-22.19%2B-339933?style=flat-square&logo=node.js&logoColor=whit

agent-infrastructureai-agentsai-toolsautomationbrowser-automationcdpchromeclaude-codeclicodex

Quick Facts

Stars270
Forks3
LanguageTypeScript
CategoryMCP Server
LicenseApache-2.0
Quality Score66.3291703734369/100
Last Updated2026-09-02
Created2026-04-04
Platformsbrowser, claude-code, cli, codex, mcp, node
Est. Tokens~26k

Uni-CLI alternative? Top 6 similar tools

Looking for a Uni-CLI alternative? If you're comparing Uni-CLI 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.

  • Overture by SixHq · ⭐ 630

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • hanzi-browse by hanzili · ⭐ 177

    let any ai agent use the local browser

  • browser-debugger-cli by szymdzum · ⭐ 148

    CLI tool for agents to quickly access browser telemetry (DOM, network, console) via Chrome DevTools Protocol.

  • deterministic-agent-control-protocol by elliot35 · ⭐ 89

    Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTT

  • claude-emporium by Vvkmnn · ⭐ 84

    🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace

  • opentabs by opentabs-dev · ⭐ 951

    Browser automation clicks buttons. OpenTabs calls APIs.

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is Uni-CLI?

Uni-CLI is One command for every interface—search, run, and inspect real software across APIs, browsers, desktops, local tools, and MCP.. It is categorized as a MCP Server with 270 GitHub stars.

What programming language is Uni-CLI written in?

Uni-CLI is primarily written in TypeScript. It covers topics such as agent-infrastructure, ai-agents, ai-tools.

How do I install or use Uni-CLI?

You can find installation instructions and usage details in the Uni-CLI GitHub repository at github.com/olo-dot-io/Uni-CLI. The project has 270 stars and 3 forks, indicating an active community.

What license does Uni-CLI use?

Uni-CLI is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to Uni-CLI?

The top alternatives to Uni-CLI on Agent Skills Hub include Overture, hanzi-browse, browser-debugger-cli. 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