Node Hardware
Report CPU, memory, disk, network, GPU and process information for local or remote nodes.
claude mcp add --scope project clio-node-hardware -- clio-kit mcp-server node-hardware
Install the launcher first. Restart your client after setup. Configuration locations →
Check the connection
clio-kit doctor --server node-hardware --connect
Checks prerequisites and tool discovery. Test on known input to verify results. Native backends may require additional setup.
Tools
get_cpu_infoGet CPU specifications, core counts, frequencies, and per-core usage.
get_memory_infoGet RAM and swap capacity, usage percentages, and availability.
get_system_infoGet OS details, hostname, uptime, and active users.
get_disk_infoGet disk partitions, usage statistics, and I/O counters.
get_network_infoGet network interfaces, IP addresses, and I/O statistics.
get_gpu_infoGet GPU model, memory, temperature, and utilization via nvidia-smi/rocm-smi.
get_sensor_infoGet temperature, fan speed, and battery sensor readings.
get_process_infoGet running processes with CPU, memory, and status details.
get_performance_infoGet real-time CPU, memory, disk, and network performance metrics.
get_remote_node_infoCollect hardware info from a remote node via SSH. Supports component filtering.
health_checkVerify server health and hardware monitoring capability status.
Examples
Replace example paths with your own files and check the returned results.
MCP tools return plain structured JSON with operation, success, data, summary, metadata, insights and hostname. Read hardware fields such as data.partitions directly; no nested JSON decoding or emoji-key matching is needed.
1. Local Hardware Overview
I need a comprehensive overview of my local system's hardware including CPU, memory, disk, and network components.
Tools called:
get_system_info,get_cpu_info,get_memory_info,get_disk_infoandget_network_info- Inspect local system components- Components collected: cpu, memory, disk, network, system, summary
2. Remote Server Monitoring
Monitor the hardware status of a remote server via SSH, focusing on CPU and memory utilization for performance analysis.
Tools called:
get_remote_node_info- Connect to remote host with SSH authentication- Components collected: cpu, memory, performance, system
3. GPU and Thermal Monitoring
Check GPU specifications and thermal sensors on both local and remote systems for machine learning workloads.
Tools called:
get_gpu_infoandget_sensor_info- Local GPU and sensor monitoringget_remote_node_info- Remote GPU and thermal analysis- Components collected: gpu, sensors, performance
4. System Health Assessment
Perform a comprehensive health check of system capabilities and verify all monitoring tools are working correctly.
Tools called:
health_check- System health verification and diagnostic assessmentget_system_infoandget_performance_info- Local system information and performance metrics
5. Performance Bottleneck Analysis
Identify performance bottlenecks on a production server by analyzing CPU, memory, disk I/O, and running processes.
Tools called:
get_remote_node_info- Remote performance analysis via SSH- Components collected: cpu, memory, disk, performance, processes
6. Storage and Network Analysis
Analyze storage health and network interface performance on multiple systems for infrastructure monitoring.
Tools called:
get_disk_infoandget_network_info- Local storage and network analysisget_remote_node_info- Remote storage and network monitoring- Components collected: disk, network, system, summary