Skip to content
appsgit

Browser MCP Agent

Browser MCP Agent is an agent skill (a SKILL.md file) from antibrow/anti-detect-browser-skills. Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level… It works with Claude Code and Gemini CLI and has 914 GitHub stars across a repository of 3 listed skills.

github.com/antibrow/anti-detect-browser-skills/browser-mcp-agent (opens in a new tab)

  • Multi-skill repo
  • Plugin marketplace
  • Needs API key
  • Coding
  • Actively maintained
View on GitHub (opens in a new tab)View on skills.sh (opens in a new tab)

Add this skill

Claude

This repository is a Claude Code plugin marketplace. In Claude Code:

/plugin marketplace add antibrow/anti-detect-browser-skills
/plugin install anti-detect-browser-skills@antibrow

In the Claude apps, zip the browser-mcp-agent folder and upload it under Customize > Skills > + > Upload a skill (code execution must be on).

ChatGPT / Codex

Codex reads skills from .agents/skills/ in a repo or ~/.agents/skills/ for every project:

git clone --depth 1 https://github.com/antibrow/anti-detect-browser-skills.git
cp -r anti-detect-browser-skills/browser-mcp-agent .agents/skills/browser-mcp-agent   # repo; ~/.agents/skills for all projects

Standalone skills also load in the ChatGPT desktop app.

Cursor

Cursor loads skills from .cursor/skills/ (or ~/.cursor/skills/) and also reads .claude/skills/:

git clone --depth 1 https://github.com/antibrow/anti-detect-browser-skills.git
cp -r anti-detect-browser-skills/browser-mcp-agent .cursor/skills/browser-mcp-agent   # project; ~/.cursor/skills for all projects

Source (checked Oct 7, 2026): code.claude.com/docs/en/skills (opens in a new tab), code.claude.com/docs/en/plugin-marketplaces (opens in a new tab), support.claude.com/en/articles/12512180-using-skills-in-claude (opens in a new tab), learn.chatgpt.com/docs/build-skills (opens in a new tab), cursor.com/docs/context/skills (opens in a new tab)

What this skill does

Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level real-device fingerprint and a persistent profile, so the session stays logged in between runs and pages see one coherent device instead of a headless build. No Playwright or SDK code to write.

When it triggers

  • Use when an agent should operate a site itself, when a computer-use / browser-use setup needs a captured real fingerprint rather than a synthetic one, when agent sessions keep losing their login, or when comparing hosted agent-browser servi

More skills in antibrow/anti-detect-browser-skills

3 skills are listed from this repository.

Similar skills

More coding skills

All Coding

FAQ

Browser MCP Agent FAQ

Still curious? Email info@appsgit.com.

What is the Browser MCP Agent skill?

Browser MCP Agent is an agent skill (a SKILL.md file) from antibrow/anti-detect-browser-skills. Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level… It works with Claude Code and Gemini CLI and has 914 GitHub stars across a repository of 3 listed skills. Its SKILL.md lives at github.com/antibrow/anti-detect-browser-skills/browser-mcp-agent.

How do I install the Browser MCP Agent skill?

In Claude Code, run /plugin marketplace add antibrow/anti-detect-browser-skills and then /plugin install anti-detect-browser-skills@antibrow. For Codex or Cursor, copy the browser-mcp-agent folder into .agents/skills/ or .cursor/skills/.

Is the Browser MCP Agent skill free?

Yes. The repository is open source under the MIT license. The skill mentions an API key or token for an external service, which may need its own account.

Is Browser MCP Agent maintained?

The repository's most recent commit was on Aug 28, 2026. appsgit only lists skills from repositories with a commit in the last six months.