Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
mcp
Browser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
6.7kstars
521forks
TypeScript
browser-automationbrowser-extensionclaudecursormcpmcp-server
Quality signals
StaleNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
Lets AI tools directly control your real browser to automate tasks while keeping your login sessions and avoiding bot detection.
Use this when
- You need AI to interact with logged-in websites
- Automating repetitive browser tasks locally
- Avoiding CAPTCHAs and bot detection
- Running AI-driven workflows that require real browser sessions
- Testing web apps with authentic user behavior
Don't use when
- You need to scrape public data without login requirements
- Running headless automation in a cloud server
- When you need to bypass strict enterprise security policies
Capabilities
- Controls your existing Chrome/Edge browser instance
- Preserves your logged-in sessions and cookies
- Uses your real browser fingerprint to avoid detection
- Runs automation locally for lower latency
- Supports AI assistants like VS Code, Claude, Cursor
- Avoids creating new browser instances to reduce overhead
InstallMCPRun via npx (Node)
Universal installANY TOOL
$ npx skillcity@latest BrowserMCP/mcpAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor or Cline.
Requires Node.js 18+ (ships with npx).
Or install manually
npx -y mcp
MCP Configuration
Add this to your claude_desktop_config.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"mcp"
]
}
}
}Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
mcp — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt