Mcproxy
MCProxy is a remote headless browser automation tool based on the MCP protocol. It allows AI agents to control browser sessions through geographically distributed SaladCloud containers for scenarios such as regional price checks, geolocation - based content verification, and web automation.
2.5 points
6.1K

What is MCProxy?

MCProxy is an innovative browser automation solution that enables AI assistants (such as Claude, Cursor, etc.) to remotely control real browsers running in SaladCloud containers through the MCP protocol. Different from traditional local browser automation, MCProxy allows you to initiate browser sessions from different geographical locations around the world, which is particularly useful for tasks that require geolocation data.

How to use MCProxy?

Using MCProxy is very simple: First, configure your MCP client (such as Claude Desktop or the VS Code extension) to connect to the MCProxy server. Then, the AI assistant can create browser sessions, navigate web pages, click elements, fill out forms, etc. through natural language instructions. All browser operations are executed in the remote SaladCloud containers, and you don't need to install any browsers locally.

Use Cases

MCProxy is particularly suitable for the following scenarios: cross - regional price comparison, georestricted content access testing, multi - regional website function verification, automated data collection, competitor analysis, website compatibility testing, etc. For example, you can access the same e - commerce website from different locations in the United States, Europe, and Asia simultaneously to compare price differences and promotional activities.

Main Features

Multi - Browser Support
Supports three browser engines: Chromium, Firefox, and WebKit (Safari). You can choose the most suitable browser type according to your needs.
Mobile Device Simulation
Comes with over 100 mobile device simulators, including iPhone, iPad, Pixel, Galaxy, etc., which can accurately simulate device resolution, user agent, and touch interaction.
Geolocation Awareness
Each browser session reports its real geolocation information (IP address, city, country, time zone, ISP). AI assistants can reference sessions by location.
Anti - Detection Technology
Built - in incognito mode. Reduces the risk of being recognized as automated by websites through technologies such as WebGL camouflage and browser fingerprint overwriting.
Human - Like Interaction
Supports click, typing, and scrolling modes that simulate human behavior, including random delays and curved mouse movements, to improve the success rate of automation.
Cloudflare Automatic Handling
Automatically detects and waits for Cloudflare challenges to complete. Supports the processing of various captcha types such as reCAPTCHA and hCaptcha.
Cookie Management
Full cookie saving and restoration functions. Supports session persistence and cross - session state maintenance, suitable for automated tasks that require login.
Coordinate Click Support
Supports click operations based on relative coordinates (in the range of 0 - 1), which is particularly suitable for visual AI agents to perform precise clicks after screenshot analysis.
Advantages
No need for local browsers: All browser operations are executed in remote containers, saving local resources.
Geographical distribution: Sessions can be initiated from different locations around the world to obtain real geolocation data.
Easy integration: Seamlessly integrates with mainstream AI assistants through the standard MCP protocol.
Highly configurable: Supports multiple browser types, device simulations, and interaction modes.
Enterprise - level reliability: Based on the SaladCloud container platform, providing a stable operating environment.
Cost - effective: Use container resources on - demand without maintaining a permanent browser infrastructure.
Limitations
Network latency: Remote operations may have higher latency than local browsers.
Dependence on SaladCloud: Requires a SaladCloud account and container deployment.
Learning curve: Requires understanding of the MCP protocol and basic configuration concepts.
Some advanced features may require additional configuration or custom development.
May not be ideal for real - time interaction scenarios that require extremely low latency.

How to Use

Environment Preparation
Ensure that you have a Docker environment or Node.js 20+ and a SaladCloud account (for production deployment).
Quick Start (Using Docker)
Use the pre - built Docker image to quickly start the browser server.
Configure the MCP Client
Configure the MCP server connection according to the AI assistant you are using. Here is an example of configuring Claude Desktop:
Create the First Session
Create the first browser session through the AI assistant. You can specify parameters such as browser type and device simulation.
Start Automation
Use natural language instructions to control the browser, such as navigation, clicking, filling out forms, taking screenshots, etc.

Usage Examples

Cross - Regional Price Comparison
Access e - commerce websites from different geographical locations to compare the price differences of the same product, including taxes and shipping fees.
Mobile Compatibility Testing
Use different mobile device simulators to test the responsive design and mobile functions of the website.
Competitor Analysis
Automatically collect product information, pricing strategies, and promotional activities from competitor websites.
Georestricted Content Access
Test the content availability and access restrictions of the website in different countries.

Frequently Asked Questions

Is MCProxy free?
Which AI assistants are supported?
How to avoid being recognized as a robot by websites?
Can it handle captchas?
How long can a session run?
How to ensure security?
Does it support JavaScript execution?
How to debug problems?

Related Resources

GitHub Repository
The complete source code, issue tracking, and contribution guidelines of MCProxy.
MCP Protocol Documentation
The official specification of the Model Context Protocol to understand how MCP works.
SaladCloud Portal
Create and manage SaladCloud container groups and obtain WebSocket endpoints.
Docker Image Repository
Pre - built Docker images, including the browser server and the MCP server.
Playwright Documentation
Documentation for the browser automation framework used by MCProxy at the bottom layer.
Community Support
Discuss issues, share use cases, and get help with other users.

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "mcproxy": {
      "command": "docker",
      "args": [
        "run", "--rm", "-i", "--network=host",
        "-e", "MCPROXY_AUTH_TOKEN=your-secret-token",
        "-e", "MCPROXY_DEFAULT_ENDPOINT=wss://your-salad-endpoint.salad.cloud",
        "ghcr.io/saladtechnologies/mcproxy/mcp-server:latest"
      ]
    }
  }
}

{
  "mcpServers": {
    "mcproxy": {
      "command": "node",
      "args": ["/path/to/mcproxy/mcp-server/dist/index.js"],
      "env": {
        "MCPROXY_AUTH_TOKEN": "your-secret-token",
        "MCPROXY_DEFAULT_ENDPOINT": "wss://your-salad-endpoint.salad.cloud"
      }
    }
  }
}

{
  "mcpServers": {
    "mcproxy": {
      "command": "node",
      "args": ["./mcp-server/dist/index.js"],
      "env": {
        "MCPROXY_AUTH_TOKEN": "your-secret-token",
        "MCPROXY_DEFAULT_ENDPOINT": "wss://your-salad-endpoint.salad.cloud"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
4.5K
4.5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
5.7K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
7.3K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
7.5K
5 points
R
Rsdoctor
Rsdoctor is a build analysis tool specifically designed for the Rspack ecosystem, fully compatible with webpack. It provides visual build analysis, multi - dimensional performance diagnosis, and intelligent optimization suggestions to help developers improve build efficiency and engineering quality.
TypeScript
9.4K
5 points
N
Next Devtools MCP
The Next.js development tools MCP server provides Next.js development tools and utilities for AI programming assistants such as Claude and Cursor, including runtime diagnostics, development automation, and document access functions.
TypeScript
10.8K
5 points
T
Testkube
Testkube is a test orchestration and execution framework for cloud-native applications, providing a unified platform to define, run, and analyze tests. It supports existing testing tools and Kubernetes infrastructure.
Go
6.5K
5 points
M
MCP Windbg
An MCP server that integrates AI models with WinDbg/CDB for analyzing Windows crash dump files and remote debugging, supporting natural language interaction to execute debugging commands.
Python
11.5K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
24.4K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
20.4K
4.5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
34.3K
5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
71.9K
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
31.1K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
65.4K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
21.0K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
48.6K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase