kogiqa-mcp — security grade SAFE, quality 72/100

Security audit verdict: SAFE · quality 72/100

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 atagon-GmbH · MCP Server · ★ 103

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

🔒 Is kogiqa-mcp safe to install? View the security audit →

About kogiqa-mcp

kogiQA MCP Web Browser A Model Context Protocol (MCP) server that provides browser automation capabilities using kogiQA. This server enables LLMs to interact with web pages through natural language, bypassing the need for screenshots or visually-tuned models. kogiQA MCP vs Playwright MCP The kogiQA MCP Server provides a browser which incorporates the capabilities of the kogiQA browser control algorithm. This enables agents to interact with pages without a selector, saving time and tokens. Requirements Node.js 20 or newer VS Code, Cursor, Windsurf, Claude Desktop, Goose, Junie or a other MCP client Installation Auto install: Claude Code VS Code Click one of the buttons below to install directly in vs code: [](https://insiders.vscode.dev/redirect?url=vscode-insiders%3Amcp%2Finstall%3F%7B%22name%22%3A%22kogiqa-browser%22%2C%22command%22%3A%22npx%22%2C%22arg

ai-agentautomationbrowser-automationheadless-browserheadless-chromellmmcpmcp-servermcp-toolsplaywright

Quick Facts

Stars103
Forks7
LanguageJavaScript
CategoryMCP Server
LicenseMIT
Quality Score72.4731816462461/100
Last Updated2026-09-08
Created2026-07-02
Platformsbrowser, mcp, node
Est. Tokens~5k

Compatible Skills

These tools work well together with kogiqa-mcp for enhanced workflows:

kogiqa-mcp alternative? Top 6 similar tools

Looking for a kogiqa-mcp alternative? If you're comparing kogiqa-mcp 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.

  • camofox-mcp by redf0x1 · ⭐ 99

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

  • camofox-browser by redf0x1 · ⭐ 355

    Anti-detection browser server for AI agents — REST API wrapping Camoufox engine with OpenClaw plugin support

  • apitap by n1byn1kt · ⭐ 124

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

  • cloakbrowser-mcp by swimmwatch · ⭐ 62

    ⚡ CloakBrowser MCP server for AI agents: Playwright-powered browsing, clean tool forwarding, Docker support, a

  • web-agent-protocol by OTA-Tech-AI · ⭐ 505

    🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support

  • agentql-mcp by tinyfish-io · ⭐ 179

    Model Context Protocol server that integrates AgentQL's data extraction capabilities.

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular JavaScript Agent Tools

Frequently Asked Questions

What is kogiqa-mcp?

kogiqa-mcp is This web browser has been designed to help your agent debug and develop complex web applications. (MCP Server). It is categorized as a MCP Server with 103 GitHub stars.

What programming language is kogiqa-mcp written in?

kogiqa-mcp is primarily written in JavaScript. It covers topics such as ai-agent, automation, browser-automation.

How do I install or use kogiqa-mcp?

You can find installation instructions and usage details in the kogiqa-mcp GitHub repository at github.com/atagon-GmbH/kogiqa-mcp. The project has 103 stars and 7 forks, indicating an active community.

What license does kogiqa-mcp use?

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

What are the best alternatives to kogiqa-mcp?

The top alternatives to kogiqa-mcp on Agent Skills Hub include camofox-mcp, camofox-browser, apitap. 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