System Resource Monitor MCP Server
Monitors system resources in real-time, including CPU, memory, disk, network, battery, and internet speed.
System Resource Monitor MCP Server
An MCP server that provides Claude with real-time system monitoring capabilities, including CPU, memory, disk, network, battery, and internet speed metrics using systeminformation and multi-source speed tests.

Tools
-
get_cpu_usage
- Retrieves the current CPU load as a percentage, including overall and per-core usage.
- Inputs: None
- Output: Text (e.g.,
CPU Load: 12.34% (Cores: 10.50, 15.20, 8.90, 14.60%))
-
get_memory_usage
- Reports total, used, and free memory in GB, plus percentage used.
- Inputs: None
- Output: Text (e.g.,
Memory: 65.43% used (7.82GB / 16.00GB))
-
get_disk_space
- Shows disk usage for the largest drive in GB and percentage.
- Inputs: None
- Output: Text (e.g.,
Disk (/): 78.90% used (189.50GB / 250.00GB))
-
get_network_usage
- Returns real-time network RX/TX rates (KB/s) and total data since boot (MB).
- Inputs: None
- Output: Text (e.g.,
Network (eth0): RX: 25.50KB/s, TX: 10.20KB/s (Total: RX 150.34MB, TX 75.89MB))
-
get_battery_status
- Provides battery charge percentage, charging status, and time remaining (if applicable).
- Inputs: None
- Output: Text (e.g.,
Battery: 85% (charging), 120 min remainingorNo battery detected)
-
get_internet_speed
- Measures internet speed using multiple download sources (including a user-uploaded file) and upload tests, returning median speeds in Mbps.
- Inputs: None
- Output: Text (e.g.,
Internet Speed: Download 45.67Mbps, Upload 8.45Mbps)
Configuration
Step 1: Clone and Install
Clone this repository:
git clone [email protected]:abhinav7895/system-mcp.git
Navigate to the directory and install dependencies:
cd system-resource-monitor && npm install
Step 2: Build the Project
Compile the TypeScript code:
npm run build
This generates the dist/index.js file, ready to run as an MCP server.
Step 3: Configure Claude Desktop
- Download Claude Desktop here.
- Add this to your
claude_desktop_config.json:
{
"mcpServers": {
"system-resource-monitor": {
"command": "node",
"args": ["/absolute/path/to/dist/index.js"]
}
}
}
Access the config file:
vim ~/Library/Application\ Support/Claude/claude_desktop_config.json
(Adjust the path to dist/index.js based on your project location.)
Step 4: Testing
Ensure Claude Desktop recognizes the tools by checking for the hammer icon:

Click the hammer icon to see available tools:

If all six tools (get_cpu_usage, get_memory_usage, etc.) appear, the integration is active. You can now ask questions like:
- "Whatβs my CPU usage?"
- "How fast is my internet?"
Step 5: Advanced Customization
- Internet Speed Test: Modify
testUrlsinindex.tsto use different download sources or adjustuploadSizeBytes(default 80KB) for upload tests. - Logging: Console logs provide detailed test output; disable them in production by removing
console.logstatements.
Troubleshooting
- Tool Not Showing: Verify the server is running (
node dist/index.js) and the config path is correct. - Internet Speed Errors: Ensure network connectivity and test URLs are accessible. Check console logs for specific failures.
- Refer to the MCP troubleshooting guide
License
This MCP server is licensed under the MIT License. You are free to use, modify, and distribute the software under the terms of the MIT License. See the LICENSE file for details.
Related Servers
Kone.vc
sponsorMonetize your AI agent with contextual product recommendations
Browser Control MCP
Enables AI agents to control a local browser, manage tabs, and conduct research via a browser extension.
Ghost CMS
Automate Ghost CMS with full CRUD operations, bulk actions, and advanced features.
RUNN
runn.io MCP Server
GitHub Knowledge Base MCP
MCP server to connect to and use any public GitHub repo as knowledge base (markdown/notebook docs)
Puzld MCP
Expose your local AI agent CLIs through one MCP endpoint
MCP Workflow Orchestration Server
Enables AI agents to discover, create, and execute complex, multi-step workflows defined in simple YAML files.
Google Tasks
Manage your Google Tasks with an AI assistant using natural language.
TaskMateAI
An AI-driven task management application controllable via MCP, supporting tasks, subtasks, priorities, and progress tracking.
ClickUp MCP Server
Apify-hosted MCP server for ClickUp with 20 tools. Tasks, spaces, folders, lists, views, docs, and custom fields. No local setup needed.
Multi-Carrier Shipping API β powered by Secureship
Secureship MCP gives AI assistants access to a multi-carrier shipping API covering rate comparison, label generation, package tracking, pickup scheduling, address book management, shipment history, customs documents, and more β across carriers like UPS, FedEx, Purolator, Canpar, and others. Browse 150+ live endpoint schemas, parameters, and auth details β always current, never stale.