Browser Mcp Agent

Browser MCP Agent gives an AI agent its own real browser through MCP tool calls: launch, navigate, click, fill, screenshot, extract text, and run JS, with no Playwright code to write. The notable part is the fingerprint. Spoofing happens inside the Chromium kernel rather than through injected JavaScript, so Canvas, WebGL, audio, and timezone all agree with each other, and sessions persist so the agent stays logged in between runs. Reach for it when an agent should operate a site itself, or when a generic headless browser keeps getting flagged. The honest caveat is the supply chain: the kernel is a closed-source binary fetched on first launch, so pin the npm version and prefetch the kernel into an image you control before running it anywhere that matters. It also won't guarantee a pass against enterprise bot managers.

skills.sh installs: 123.9K
GitHub stars: 21
last updated: Oct 26, 2026

View on GitHub

Install

$ npx -y skills add antibrow/anti-detect-browser-skills --skill browser-mcp-agent --agent claude-code

Installs into .claude/skills of the current project.

Files

Browser MCP Agent

Run antibrow as an MCP server so an AI agent can launch and control a real, fingerprinted browser directly through tool calls - no Playwright code, no custom automation script. The agent navigates, clicks, fills forms, and reads pages itself.

npm package: anti-detect-browser (Node >= 18) - ships the MCP server built in
PyPI package: antibrow (Python 3.9 - 3.13) - pip install "antibrow[mcp]" for a stdio MCP server example
Dashboard: https://antibrow.com
Full SDK / REST API reference: see the anti-detect-browser skill

Authorized use only. Point this at sites and accounts you own or are permitted to operate: your own apps, your own accounts, publicly available pages, your own bot detection under test. Do not use it to reach systems without authorization, to log into accounts that are not yours, to create fake accounts or engagement, or to work around a platform's enforcement decision. Respect each site's terms, robots.txt and rate limits - see Acceptable use.

SKILL.md on GitHub