oya-browser — security grade SAFE, quality 64/100

Security audit verdict: SAFE · quality 64/100

Flagged: environment access. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by OyadotAI · MCP Server · ★ 202

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

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

About oya-browser

OpenRouter for browsers. One API over Oya Cloud, Browserbase, Steel, Anchor, Browser Use and your own Chrome. Turn a portal task into a reusable playbook. Replay with new inputs, review agent repairs, and bring in a person when a run needs help. <img src="https://img.shields.io/badge/hosted-browser.getoya.ai-141410?logo

ai-agentsai-browseranti-detectbrowser-automationbrowser-infrastructurebrowser-usecdpheadless-chromemcpplaywright

Quick Facts

Stars202
Forks190
LanguageTypeScript
CategoryMCP Server
Quality Score63.6866008932477/100
Last Updated2026-09-20
Created2026-03-15
Platformsbrowser, mcp, node
Est. Tokens~18k

Compatible Skills

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

  • Interceptor — semantic(0.56)+complementary+rare_topics+same_lang+similar_pop+shared_platform (74%)
  • bux — semantic(0.63)+complementary+rare_topics+similar_pop+shared_platform (71%)
  • CloakBrowser — semantic(0.48)+complementary+rare_topics+same_lang+similar_pop+shared_platform (71%)

oya-browser alternative? Top 6 similar tools

Looking for a oya-browser alternative? If you're comparing oya-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.

  • open-browser-use by iFurySt · ⭐ 303

    🔮 Platform-neutral Browser Use for AI agents: real Chrome automation with a CLI + SDKs, no lock-in, dead simp

  • multizen-browser by multizenteam · ⭐ 149

    Anti-detect browser for AI agents and human operators. Isolated Chromium profiles (cookies, fingerprint, proxy

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

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

  • camofox-browser by redf0x1 · ⭐ 355

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

  • Uni-CLI by olo-dot-io · ⭐ 270

    One command for every interface—search, run, and inspect real software across APIs, browsers, desktops, local

  • bluebox by VectorlyApp · ⭐ 200

    Index the world's undocumented 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 oya-browser?

oya-browser is The browser control plane for AI agents. One API over Oya Cloud, Browserbase, Steel, Anchor, Browser Use and your own Chrome, with persistent personas, CAPTCHA and MFA handling, and live human takeove. It is categorized as a MCP Server with 202 GitHub stars.

What programming language is oya-browser written in?

oya-browser is primarily written in TypeScript. It covers topics such as ai-agents, ai-browser, anti-detect.

How do I install or use oya-browser?

You can find installation instructions and usage details in the oya-browser GitHub repository at github.com/OyadotAI/oya-browser. The project has 202 stars and 190 forks, indicating an active community.

What are the best alternatives to oya-browser?

The top alternatives to oya-browser on Agent Skills Hub include open-browser-use, multizen-browser, web-agent-protocol. 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