Camoufox MCP
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Camoufox MCP
Browser automation server for AI agents — powered by Camoufox and the Model Context Protocol.
What is Camoufox MCP?
Camoufox MCP is a production-ready MCP server that exposes browser automation capabilities to AI agents. It wraps Camoufox (a privacy-focused Firefox fork built on Playwright) behind a clean, modular API designed for agent workflows.
It is not a thin Playwright wrapper.
It is a structured browser runtime with session management, profile isolation, a security layer, and an extraction engine — all accessible through MCP tools.
Related MCP server: CamoFox MCP
Features
Session management — multiple independent browser sessions with unique IDs
Profile system — persistent browser profiles with per-profile configuration
Navigation — goto, back, forward, reload with proper wait strategies
Interaction — click, type, press, scroll with semantic selector support
Extraction — structured text, HTML, links, and metadata extraction
Screenshots — full-page, viewport, or element-level screenshots
JavaScript execution — sandboxed
browser_evaltoolTab management — open, close, switch between tabs
Download management — controlled file downloads with path safety
Security layer — permission model and URL/path validation
Structured logging — session-level traceability, plain-text and JSON modes
Graceful shutdown — no orphaned browser processes
Architecture
AI Client
│ MCP (stdio)
▼
Camoufox MCP Server
├── Tool Registry
├── BrowserManager ──► Camoufox (AsyncCamoufox)
├── SessionManager
├── ExtractionEngine
├── DownloadManager
└── Security / Permission LayerEach MCP tool follows the pattern:
MCP Tool → Service → Manager → Camoufox Adapter → BrowserInstallation
With uv (recommended)
git clone https://github.com/camoufox-mcp/camoufox-mcp
cd camoufox-mcp
uv syncFrom PyPI (once published)
uv tool install camoufox-mcpQuick Start
# 1. Copy and configure environment
cp .env.example .env
# 2. Start the MCP server
camoufox-mcp
# or with uv
uv run camoufox-mcpMCP Configuration
Add to your MCP client config (e.g. Claude Desktop claude_desktop_config.json):
{
"mcpServers": {
"camoufox": {
"command": "uv",
"args": ["run", "--directory", "/path/to/camoufox-mcp", "camoufox-mcp"]
}
}
}Available Tools (Phase 1)
Tool | Description |
| Launch a new browser session |
| Close an existing session |
| List active sessions |
More tools are added in subsequent phases — see docs/tools.md.
Configuration
All settings are controlled via environment variables.
See .env.example and docs/configuration.md.
Development
# Install with dev dependencies
uv sync --extra dev
# Lint
uv run ruff check src/
# Format
uv run ruff format src/
# Tests
uv run pytestDocker
docker build -t camoufox-mcp .
docker run --rm -i camoufox-mcpSee Dockerfile for configuration options.
Security
This project is designed for legitimate browser automation, testing, research, and accessibility workflows. See docs/security.md for the full security model.
Roadmap
Phase 2: Navigation, tabs, session persistence
Phase 3: Click, type, press, scroll, wait
Phase 4: Extraction engine (text, HTML, links, structured data)
Phase 5: Screenshots, downloads
Phase 6: Security / permission layer
Phase 7: Unit + integration tests
Phase 8: Full documentation
Phase 9: PyPI release, Docker image
License
MIT — see LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Web scraping, browser automation, screenshots and AI data extraction for AI agents via MCP.
Stealth web browser for agents: search, fetch, click, download and type in persistent MCP sessions.
Control a real browser from AI agents: navigate, click, type, screenshot, read the page.
Browz hosted MCP (free public beta): let an AI app drive your own Browz browser profiles from anywhere. Connect https://mcp.gobrowz.com/mcp and sign in with your Browz account (OAuth) or an agent token. Each call is relayed to the Browz app on your computer, which must be online with Remote control on and have a hardware security chip (Mac Secure Enclave or TPM 2.0). 17 tools: profiles, tabs, navigate, snapshot, act, wait, screenshot. Cookies, downloads and stored sign-ins stay on your computer.
Related MCP Servers
- AlicenseBqualityCmaintenanceEnables LLMs to drive a stealthy, fingerprint-spoofed Firefox browser via MCP tools, supporting navigation, interaction, extraction, and multi-session management.8440 PyPI1MIT
- AlicenseNot gradedqualityAmaintenanceGives MCP-compatible AI agents an anti-detection browser toolset for navigating, interacting with, searching, and extracting content from websites, plus downloads, multi-tab workflows, and persistent sessions with cookies and saved profiles. It enables reliable automation of the web without getting blocked by running against a separate Camoufox-based browser server.581 npmMIT
- AlicenseNot gradedqualityAmaintenanceExposes a 47-tool browser automation surface to MCP clients, enabling AI agents to navigate, interact with, observe, and extract content from web pages across multi-tab sessions. Runs on Camoufox-based anti-detection behavior so agents can automate sites that block conventional headless browsers, with session persistence, cookie import, and stdio or HTTP transport.581 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables MCP-compatible AI agents to automate anti-detection browser sessions with navigation, interaction, search, extraction, downloads, multi-tab workflows, and session reuse.581 npmMIT