Bridge MCP: AI-Controlled Windows PC Server with Multi-Function Integration

Bridge MCP

Bridge MCP is a Windows PC control server based on the Model Context Protocol (MCP), allowing any AI to fully control the computer through a local proxy program, including application control, mouse and keyboard operations, screen capture, system command execution, browser automation, and clipboard management.

Operating system automation Artificial intelligence chatbots #PC Control #AI Automation #Windows Tools #Desktop Proxy .Python

rating : 2.5 points

downloads : 8.4K

update time : 2026-03-12

Open Site

What is Bridge MCP?

Bridge MCP is an intelligent computer control tool that allows AI assistants (such as Claude, ChatGPT, etc.) to operate your Windows computer like a real person. Through this tool, AI can help you open software, input text, click the mouse, view screen content, browse the web, etc., to achieve various automated tasks.

How to use Bridge MCP?

Using Bridge MCP is very simple: 1) Run the local proxy program on your computer; 2) Configure the connection in the AI assistant; 3) Tell the AI what tasks you want to complete. The AI will automatically use appropriate tools to operate your computer.

Use Cases

Bridge MCP is particularly suitable for the following scenarios: automating repetitive computer operations, remote assistance for problem - solving, batch processing of files, web data collection, software testing automation, teaching demonstrations, etc.

Main Features

Application Control

Application management functions such as starting, switching, closing, and resizing windows

Input Automation

Simulate mouse clicks, keyboard input, shortcut key operations, etc.

Screen Viewing and Analysis

Take real - time screenshots, obtain desktop status, and identify interface elements

Browser Control

Control the Chrome browser, navigate web pages, click links, and fill out forms

System Command Execution

Run PowerShell and CMD commands, perform file read and write operations

Safety Protection Mechanism

Dangerous operations require manual confirmation to prevent accidental operations

Persistent Registration

One - time configuration for permanent use, supporting computer restart and AI session restart

Advantages

🤖 Enable AI assistants to operate the computer, achieving true automation

🔄 Support multiple AI platforms (Claude, ChatGPT, Cursor, etc.)

🔒 Built - in safety mechanism, dangerous operations require manual confirmation

💾 Persistent configuration, one - time setup for permanent use

🌐 Support remote access, allowing you to control the computer from anywhere

👁️ Real - time screen viewing, enabling AI to 'see' the computer screen content

Limitations

Only support Windows systems (temporarily not support macOS and Linux)

The local proxy program needs to be kept running

Recognition of some complex interface elements may not be accurate enough

The quality of the network connection affects the remote control effect

How to Use

Download and Install

Download the Bridge MCP project from GitHub and install the necessary Python dependency packages

Start the Local Proxy

Run the local proxy program on your computer, which will listen for instructions from the AI assistant

Configure the AI Client

Configure the Bridge MCP connection in the AI assistant you are using (such as Claude Desktop)

Start Using

Now you can tell the AI assistant what tasks you want to complete, and the AI will automatically operate your computer

Usage Examples

Automated Document Processing

Let the AI automatically open a Word document, adjust the format, and save it

Web Data Collection

Automatically access websites and collect specific information

Batch File Organization

Automatically organize files in the download folder

Software Installation and Configuration

Automatically download and install software

Frequently Asked Questions

Is Bridge MCP safe? Will it accidentally delete my files?

Do I need to keep local_agent.py running all the time?

Which AI assistants are supported?

Can I remotely control it from a mobile phone or another computer?

What should I do if the AI operation goes wrong?

Do I need programming knowledge to use it?

Related Resources

GitHub Project Homepage

Get the latest version of the source code and updates

FastMCP Official Website

Learn about the Model Context Protocol framework

Claude Desktop Download

Download the Claude Desktop client

Usage Tutorial Video

Video tutorials on installing and using Bridge MCP

Problem Feedback and Discussion

Report problems or propose feature suggestions

🚀 Bridge MCP

Universal PC Control for Any AI

Bridge MCP is a Model Context Protocol (MCP) server that empowers any AI to gain full control over a Windows PC. It offers a wide range of tools for application control, input automation, screen capture, web browsing, command execution, and clipboard management.

Features • Quick Start • Configuration • Tools • Troubleshooting • Contributing

🚀 Quick Start

Step 1: Clone the Repository

git clone https://github.com/BarhamAgha1/Bridge-MCP.git
cd Bridge-MCP

Step 2: Install Dependencies

pip install -r requirements-local.txt

Note: Playwright browsers (~100MB) auto-install on first use - no manual setup needed!

Step 3: Start the Local Agent

python local_agent.py

Keep this terminal open! The agent will display:

Bridge MCP Local Agent running on http://127.0.0.1:8006

Step 4: Configure Your AI Client

See Configuration below for Claude Desktop, Cursor, or VS Code setup.

Step 5: Register Your Agent

In your AI conversation, register the local agent:

Use register_agent with:
- agent_id: "my-pc"
- callback_url: "http://127.0.0.1:8006"
- agent_name: "My Windows PC"

Step 6: Start Controlling!

Now use any tool like screenshot(), click(100, 200), type_text("Hello"), app_launch("notepad"), etc.

✨ Features

Category	Tools	Description
🚀 App Control	8 tools	Launch, switch, close, resize, minimize, maximize applications
🖱️ Mouse & Keyboard	10 tools	Click, type, hotkeys, scroll, drag, move cursor
📸 Screen Capture	7 tools	Screenshots, desktop state, find UI elements
⚡ System	8 tools	PowerShell, CMD, file read/write, system info
🌐 Browser	15 tools	Chrome control, tabs, navigation, web scraping
📋 Clipboard	3 tools	Copy, paste, clear clipboard
🔧 Utilities	5+ tools	Wait, dialogs, action sequences

Total: 40+ powerful tools for complete PC automation!

📦 Installation

First-Time Setup

Start the local agent:

cd Bridge-MCP
python local_agent.py

The agent auto-registers itself - no manual registration needed!
Verify in any Claude session:

Use list_agents() to see registered agents

Running Local Agent as Background Service

For always-on access, install local_agent as a Windows service:

python install_service.py install
python install_service.py start

To remove:

python install_service.py stop
python install_service.py remove

💻 Usage Examples

Example 1: Open Notepad and Write Text

User: Open notepad and write "Hello from AI!"

AI uses:
1. app_launch("notepad")
2. wait(1)
3. type_text("Hello from AI!")

Example 2: Take a Screenshot

User: What's on my screen right now?

AI uses:
1. screenshot()
2. [AI analyzes the image and describes what it sees]

Example 3: Search on Google

User: Search for "Bridge MCP" on Google

AI uses:
1. chrome_open("https://google.com")
2. type_text("Bridge MCP")
3. press_key("enter")

📚 Documentation

🔄 How Persistence Works

Bridge MCP v2.0 stores agent registrations in a persistent JSON file:

Windows: %APPDATA%\bridge-mcp\agents.json
Linux/Mac: ~/.config/bridge-mcp/agents.json

This means:

✅ Register once, works forever
✅ Survives Claude Code session restarts
✅ Survives computer reboots
✅ Works across all AI clients

🎯 What is Bridge MCP?

Bridge MCP is a Model Context Protocol (MCP) server that gives any AI full control over a Windows PC. Whether you're using Claude, ChatGPT, Cursor, Gemini, or any other MCP-compatible AI, Bridge MCP lets you:

🖥️ Control Applications - Launch, switch, resize, close any app
🖱️ Automate Input - Mouse clicks, keyboard typing, hotkeys, scrolling
📸 See the Screen - Screenshots, UI element detection, desktop state
🌐 Browse the Web - Full Chrome automation and control
⚡ Run Commands - PowerShell, CMD, file operations
📋 Manage Clipboard - Copy, paste, clear

Think of it as giving your AI eyes and hands to control your computer!

🏗️ Architecture

Bridge MCP uses a Relay Architecture to work across platforms:

┌─────────────────┐         ┌─────────────────┐         ┌─────────────────┐
│    Any AI       │         │  Cloud Relay    │         │  Your Windows   │
│  (Claude, etc.) │◄───────►│  (bridge_mcp)   │◄───────►│  PC (Agent)     │
└─────────────────┘         └─────────────────┘         └─────────────────┘

bridge_mcp.py - MCP server (runs locally or on FastMCP Cloud)
local_agent.py - HTTP server on your PC that executes commands (port 8006)

🔧 Configuration

Claude Desktop

Open the config file at %APPDATA%\Claude\claude_desktop_config.json
Add Bridge MCP:

{
  "mcpServers": {
    "bridge-mcp": {
      "command": "python",
      "args": ["C:\\Users\\YourName\\Path\\To\\Bridge-MCP\\bridge_mcp.py"]
    }
  }
}

⚠️ Important: Replace the path with the actual location where you cloned the repository!

Example paths:

C:\\Users\\PC\\Desktop\\Bridge-MCP\\bridge_mcp.py
D:\\Projects\\Bridge-MCP\\bridge_mcp.py

Restart Claude Desktop completely (close and reopen)

Cursor

Add to your MCP settings in Cursor preferences with the same configuration format.

VS Code + Claude Code

Create .vscode/mcp.json in your project:

{
  "mcpServers": {
    "bridge-mcp": {
      "command": "python",
      "args": ["C:\\Users\\YourName\\Path\\To\\Bridge-MCP\\bridge_mcp.py"]
    }
  }
}

Remote Access (Optional)

To control your PC from anywhere, expose the local agent with ngrok:

ngrok http 8006

Then use the ngrok URL (e.g., https://xxxx.ngrok.io) as your callback_url when registering.

🛠️ Available Tools

🚀 App Control Tools

Tool	Description	Example
`app_launch`	Launch an application	`app_launch("notepad")`
`app_switch`	Switch to open app	`app_switch("Chrome")`
`app_close`	Close an application	`app_close("notepad")`
`app_list`	List all open apps	`app_list()`

🖱️ Input Tools (Mouse & Keyboard)

Tool	Description	Example
`click`	Click at coordinates	`click(500, 300)`
`double_click`	Double-click	`double_click(500, 300)`
`right_click`	Right-click	`right_click(500, 300)`
`type_text`	Type text	`type_text("Hello World!")`
`press_key`	Press a key	`press_key("enter")`
`hotkey`	Keyboard shortcut	`hotkey("ctrl,c")`
`scroll`	Scroll	`scroll("down", 3)`
`drag`	Drag and drop	`drag(100, 100, 500, 500)`
`move_mouse`	Move cursor	`move_mouse(500, 300)`

📸 Screen Tools

Tool	Description	Example
`screenshot`	Take screenshot	`screenshot()`
`get_desktop_state`	Get full desktop state	`get_desktop_state()`
`get_screen_size`	Get screen dimensions	`get_screen_size()`
`get_mouse_position`	Get cursor position	`get_mouse_position()`

⚡ System Tools

Tool	Description	Example
`run_powershell`	Run PowerShell	`run_powershell("Get-Process")`
`run_cmd`	Run CMD command	`run_cmd("dir")`
`file_read`	Read file	`file_read("C:/test.txt")`
`file_write`	Write file	`file_write("C:/test.txt", "Hello")`
`file_list`	List directory	`file_list("C:/Users")`

🌐 Browser Tools (Chrome)

Tool	Description	Example
`chrome_open`	Open Chrome	`chrome_open("https://google.com")`
`chrome_navigate`	Go to URL	`chrome_navigate("https://example.com")`

🌐 Browser Tools (Playwright - Advanced)

Tool	Description	Example
`browser_navigate`	Go to URL	`browser_navigate("google.com")`
`browser_click`	Click element (CSS)	`browser_click("#submit-btn")`
`browser_type`	Type in element	`browser_type("#search", "hello")`
`browser_press`	Press key	`browser_press("Enter")`
`browser_content`	Get page text	`browser_content()`
`browser_screenshot`	Browser screenshot	`browser_screenshot()`

📋 Clipboard Tools

Tool	Description	Example
`clipboard_copy`	Copy to clipboard	`clipboard_copy("Hello")`
`clipboard_paste`	Get clipboard	`clipboard_paste()`

🔧 Troubleshooting

Claude Desktop shows "Server disconnected"

Check the path - Make sure the path in your config points to the actual bridge_mcp.py file. The path must be absolute and use double backslashes (\\) in JSON.
Test manually - Open Command Prompt and run:

cd "C:\path\to\Bridge-MCP"
python bridge_mcp.py

It should stay running (not exit immediately). Press Ctrl+C to stop.

Install dependencies:

pip install fastmcp httpx

Restart Claude Desktop - Fully close and reopen after any config changes.

Local agent not receiving commands

Make sure local_agent.py is running in a terminal (keep it open!)
Verify the callback URL is correct when registering the agent
For local use: http://127.0.0.1:8006
For remote access: Use ngrok (ngrok http 8006) and use the ngrok URL

"No agents connected" error

You need to register your local agent first:

register_agent("my-pc", "http://127.0.0.1:8006", "My PC")

Unicode/Emoji errors on Windows

If local_agent.py crashes with Unicode errors, the terminal may not support emojis. This has been fixed in the latest version.

☁️ FastMCP Cloud Deployment

Bridge MCP can be deployed on FastMCP Cloud for easy access:

Fork this repository
Go to fastmcp.cloud
Sign in with GitHub
Create project from your forked repo
Set entrypoint: bridge_mcp.py
Deploy!

Your MCP will be available at: https://your-project.fastmcp.app/mcp

🔧 Technical Details

🔒 Enterprise-Grade Security

Bridge MCP 2.0 includes:

Auth Tokens: Uses secure Bearer tokens to prevent unauthorized access.
Auto-Config: Tokens are auto-generated and saved to agents.json.

🌐 Next-Gen Browser Automation

Click & Type: Interact with any website element.
Semantic Understanding: Read page content programmatically.
Headless Mode: Run automations invisible or visible.

🧠 Semantic Computer Vision

Bridge MCP "sees" your apps:

UI Tree: It can read the accessibility tree of Windows apps.
Precision: Knows exactly where buttons are (no more guessing pixels).

🛡️ Safety Sentinel (Human-in-the-Loop)

Bridge MCP now puts YOU in control:

Command Interception: Dangerous commands (writing files, running shell scripts) are BLOCKED by default.
Approval Overlay: Approval requests appear directly in the AI Activity Overlay with three options:
- ✓ APPROVE - Execute this one command
- ✗ DENY - Block this command
- ✓ ALWAYS APPROVE - Disable Safe Mode and approve all future commands
Dashboard Control: View all pending requests at http://localhost:8006
Safe Mode Toggle: Switch Safe Mode on/off anytime from the web dashboard
Peace of Mind: You can leave the agent running without fear of it deleting your files.

👁️ Terminator Vision (Live Observability)

See what the AI sees, in real-time:

Live Stream: The dashboard features a low-latency 1080p MJPEG stream of your desktop.
Semantic Overlay: Green bounding boxes highlight every button, link, and window the AI detects.
Debug Instantly: Visual confirmation that the AI has found the correct "Submit" button.