Camofox Mcp

The anti-detection browser MCP server for AI agents. Navigate, interact, and automate the web without getting blocked.

> New to CamoFox? Skip the docs — paste this prompt into your AI agent and it’ll verify your setup end-to-end.

How it works (TL;DR)

Your AI Agent ──(MCP)──> camofox-mcp ──(REST)──> camofox-browser ──> Camoufox (anti-detection Firefox)

CamoFox has 2 components — you need both running:

- camofox-browser is the headless browser server (anti-detection)
- camofox-mcp is the MCP bridge your AI agent connects to

---

Why CamoFox MCP?

AI agents using Playwright get blocked constantly. CAPTCHAs, fingerprint detection, IP bans — the web fights back against automation.

CamoFox MCP wraps the CamoFox Browser Server as an MCP server, giving your AI agent:

- 🛡️ Anti-detection fingerprinting — Each tab gets a unique, human-like browser fingerprint
- ⚡ Fast, token-efficient snapshots — Accessibility tree snapshots use 90% fewer tokens than screenshots
- 🔍 Built-in search — Search Google, YouTube, Amazon + 11 more engines without getting blocked
- 🍪 Session persistence — Import cookies, maintain login state across interactions
- 🎯 CSS selector fallback — Target elements even when accessibility refs aren't available

CamoFox MCP vs Playwright MCP

| Feature | CamoFox MCP | Playwright MCP |
|---------|:-----------:|:--------------:|
| Anti-detection fingerprinting | ✅ | ❌ |
| Passes bot detection tests | ✅ | ❌ |
| Search engine macros (14 engines) | ✅ | ❌ |
| Accessibility snapshots | ✅ | ✅ |
| Cookie import/export | ✅ | Limited |
| Headless support | ✅ | ✅ |
| Setup complexity | Medium | Easy |
| Token efficiency | High | High |

CamoFox MCP vs Other Camoufox MCPs

| Feature | CamoFox MCP | whit3rabbit/camoufox-mcp | baixianger/camoufox-mcp |
|---------|:-----------:|:-----------------------:|:-----------------------:|
| Tools | 35 | 1 | 33 |
| Architecture | REST API client | Direct browser | Direct browser |
| Session persistence | ✅ | ❌ (destroyed per request) | ✅ |
| Token efficiency | High (snapshots) | Low (raw HTML) | High (snapshots) |
| Search macros | ✅ (14 engines) | ❌ | ❌ |
| CSS selector fallback | ✅ | ❌ | ❌ |
| Active maintenance | ✅ | ❌ (stale 8mo) | ✅ |
| Press key support | ✅ | ❌ | ✅ |

Prerequisites

- Pick one:
- Docker (recommended) — easiest “zero-to-hero” setup
- Node.js 18+ (download) — needed for the npx setup
- CamoFox Browser Server must be running (it is not a downloadable desktop binary — use Docker, npx, or build from source)
- An MCP-compatible client: VS Code (Copilot), Cursor, Claude Desktop, or any MCP client

Quick Start

Pick ONE option below.

Option A: Docker (Recommended — Easiest)

1) Start CamoFox Browser

docker run -d -p 9377:9377 --name camofox-browser ghcr.io/redf0x1/camofox-browser:latest

2) Verify it’s running

curl http://localhost:9377/health

3) Add MCP config to your editor (see configs below)

4) Paste the verification prompt into your AI agent (see below)

Option B: npx (Quick — Needs Node.js 18+)

1) Start CamoFox Browser (keep this terminal open)

npx camofox-browser@latest

2) In another terminal, verify:

curl http://localhost:9377/health

3) Add MCP config to your editor (see configs below)

4) Paste the verification prompt into your AI agent

Option C: From Source (Developers)

1) Clone and start CamoFox Browser

git clone https://github.com/redf0x1/camofox-browser.git
cd camofox-browser && npm install && npm run build && npm start

2) Clone and build CamoFox MCP

git clone https://github.com/redf0x1/camofox-mcp.git
cd camofox-mcp && npm install && npm run build

3) Add MCP config (see configs below — use node path instead of npx)

4) Paste the verification prompt

MCP Client Configuration

VS Code (Copilot)

- File: .vscode/mcp.json (in your workspace root)
- Create the file if it doesn't exist

{
  "servers": {
    "camofox": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "camofox-mcp@latest"],
      "env": {
        "CAMOFOX_URL": "http://localhost:9377"
      }
    }
  }
}

Claude Desktop

- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json
- Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "camofox": {
      "command": "npx",
      "args": ["-y", "camofox-mcp@latest"],
      "env": {
        "CAMOFOX_URL": "http://localhost:9377"
      }
    }
  }
}

Note: Claude Desktop uses "mcpServers" not "servers".

Cursor

- File: ~/.cursor/mcp.json

{
  "mcpServers": {
    "camofox": {
      "command": "npx",
      "args": ["-y", "camofox-mcp@latest"],
      "env": {
        "CAMOFOX_URL": "http://localhost:9377"
      }
    }
  }
}

From Source (use node instead of npx)

{
  "servers": {
    "camofox": {
      "type": "stdio",
      "command": "node",
      "args": ["/absolute/path/to/camofox-mcp/dist/index.js"],
      "env": {
        "CAMOFOX_URL": "http://localhost:9377"
      }
    }
  }
}

Note: This example is for VS Code. For Claude Desktop or Cursor, use "mcpServers" instead of "servers".

3. Verify Setup

> After configuring your MCP client, restart your editor. Then paste this prompt into your AI agent:

Verify my CamoFox MCP setup. Run these checks and report results:
1) Call server_status — is the browser server connected?

2) If connected: create_tab with url https://example.com

3) navigate_and_snapshot on that tab (wait for text: "Example Domain")

4) list_profiles to confirm profile storage is accessible

5) close_tab for the test tab
If any step fails, diagnose the issue and suggest a fix.

Report: ✅ pass or ❌ fail for each step, plus overall status.

> Prerequisites: You must configure your MCP client first (Step 2 above). The AI agent can do everything else.

Manual verification (optional):

```bash
curl http://localhost:9377/health