mcp-browser-agent and camofox-mcp

mcp-browser-agent
50
Established
camofox-mcp
49
Emerging
Maintenance 10/25
Adoption 7/25
Maturity 15/25
Community 18/25
Maintenance 13/25
Adoption 7/25
Maturity 20/25
Community 9/25
Stars: 36
Forks: 12
Downloads:
Commits (30d): 0
Language: TypeScript
License: MPL-2.0
Stars: 32
Forks: 3
Downloads:
Commits (30d): 0
Language: TypeScript
License: MIT
No Package No Dependents
No risk flags

About mcp-browser-agent

imprvhub/mcp-browser-agent

A Model Context Protocol (MCP) integration that provides Claude Desktop with autonomous browser automation capabilities. This agent enables Claude to interact with web content, manipulate DOM elements, execute JavaScript, and perform API requests.

Implements Playwright-based browser automation with MCP resource management for console logs and screenshots, enabling Claude to chain complex multi-step workflows through natural language. Supports multiple browser engines (Chrome, Firefox, Edge, WebKit) and integrates a built-in HTTP client for direct API requests, allowing seamless combination of web scraping and backend interactions within single agent tasks.

About camofox-mcp

redf0x1/camofox-mcp

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

Exposes 46 specialized browser automation tools (navigation, interaction, observation, downloads, batch workflows) via MCP stdio or HTTP transport, connecting Claude Desktop, VS Code, Cursor, and OpenClaw to a separate CamoFox browser server. Built on Camoufox anti-detection techniques with token-efficient accessibility snapshots, CSS-selector fallbacks, and session persistence including cookie import and profile management. Supports both desktop MCP clients via stdio and remote agents via HTTP, with optional API-key authentication and batch workflow coordination across tracked tabs.

Scores updated daily from GitHub, PyPI, and npm data. How scores work