Anti-detection browser MCP server for AI agents — navigate, interact, and automate the web without getting blocked
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"camofox-mcp": {
"command": "<see-readme>",
"args": []
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Anti-detection browser MCP server for AI agents — navigate, interact, and automate the web without getting blocked
No automated test available for this server. Check the GitHub README for setup instructions.
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
No package registry to scan.
This server is missing a description. Tools and install config are also missing.If you've used it, help the community.
Add informationBe the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in ai-ml
Dynamic problem-solving through sequential thought chains
A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
An open-source AI agent that brings the power of Gemini directly into your terminal.
The official Python SDK for Model Context Protocol servers and clients
MCP Security Weekly
Get CVE alerts and security updates for Camofox Mcp and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
AI-powered anti-detection browser automation for MCP-compatible AI agents.
CamoFox MCP connects MCP clients such as Claude Desktop, VS Code, Cursor, and OpenClaw to the CamoFox browser server. It gives agents a practical browser toolset for navigation, interaction, search, extraction, downloads, and session reuse while relying on Camoufox-based anti-detection behavior underneath.
You need both components running:
camofox-browser handles the anti-detection browser.camofox-mcp exposes that browser to your MCP client.npx + stdioStart the browser server:
npx camofox-browser@latest
Add CamoFox MCP to your MCP client:
{
"servers": {
"camofox": {
"type": "stdio",
"command": "npx",
"args": ["-y", "camofox-mcp@latest"],
"env": {
"CAMOFOX_URL": "http://localhost:9377"
}
}
}
}
Start the browser server:
docker run -d -p 9377:9377 --name camofox-browser ghcr.io/redf0x1/camofox-browser:latest
Run CamoFox MCP in HTTP mode for remote MCP clients such as OpenClaw:
docker run -p 3000:3000 --rm \
-e CAMOFOX_TRANSPORT=http \
-e CAMOFOX_URL=http://host.docker.internal:9377 \
ghcr.io/redf0x1/camofox-mcp:latest node dist/http.js
Full client configuration examples live in docs/getting-started.md.
Verify the browser server is reachable:
curl -fsS http://localhost:9377/health
Expected response includes "ok":true and "browserConnected":true.
| Category | Tool count | Docs |
|---|---|---|
| Health | 1 | Health |
| Tabs | 3 | Tabs |
| Navigation | 4 | Navigation |
| Interaction | 8 | Interaction |
| Observation | 8 | Observation |
| Search | 1 | Search |
| Session | 4 | Session |
| Profiles | 4 | Profiles |
| Downloads | 3 | Downloads |
| Extraction | 3 | Extraction |
| Batch workflows | 6 | Batch |
| Presets | 1 | Presets |
camofox-browser server separately.CAMOFOX_API_KEY on both sides.Treat this as a browser control surface. In shared or networked environments, isolate the browser server, avoid exposing MCP endpoints broadly, and use CAMOFOX_API_KEY when authentication is enabled. Session profiles can contain sensitive cookies and should be stored accordingly.
Start at docs/README.md for the documentation hub, then use docs/getting-started.md for setup, verification, and first workflow exam