System Info MCP Assistant

    2

    Monitor CPU, memory, and disk usage, diagnose performance bottlenecks, and safely manage local processes through MCP.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    System Info MCP Assistant

    Example session with this skill installed

    My computer is feeling really sluggish. Can you check what's going on with my CPU and RAM, and see if any specific process is hogging resources?

    • Read your context and instructions
    • Compiled the system info mcp

    I have performed a system health check and identified a significant memory bottleneck caused by a background process.

    Local System Health Report

    MetricCurrent ValueStatus
    CPU Usage12.4%Normal
    RAM Usage94.2% (15.1GB / 16.0GB)Critical
    Disk Usage68% (340GB / 500GB)Normal
    Uptime4 days, 02:14:55Stable
    Network2.5 Mbps Down / 0.8 Mbps UpNormal

    Top Resource Consumers

    Process NamePIDCPU %RAM %
    Docker Desktop48212.142.5
    Node.js (Server)192031.518.2
    Chrome Helper88210.812.4
    Python (Zombie)552100.18.9

    Analysis: Your RAM is nearly exhausted at 94% utilization. While CPU usage is low, the high memory pressure is likely causing the sluggishness due to disk swapping. The Docker Desktop and Node.js instances are the primary consumers. I also noticed a Python process (PID 55210) that appears to be orphaned.

    Next steps

    1. Close unused browser tabs or restart Docker to free up approximately 7GB of RAM.
    2. If the Python process (PID 55210) is unresponsive, I can terminate it for you.
    3. Shall I re-scan the resource usage after you close those applications?

    Connects securely to your tools. The creator never sees your data.

    About this skill

    System Info MCP Assistant

    Diagnose local system performance issues and safely manage processes using your AI agent.

    System Info MCP Assistant connects your AI workflow to the open-source MCP-system-info server, giving agents access to real system metrics instead of relying on assumptions or manually executed terminal commands.

    What it does

    • System monitoring: Retrieve current CPU, RAM, disk, network, and uptime information.
    • Resource diagnostics: Identify processes consuming excessive CPU or memory.
    • Process inspection: List running processes to help investigate system performance.
    • Safe process management: Request explicit user confirmation before terminating a specific process, with additional server-side validation.

    How it works

    1. Assess system health: Retrieve system metrics using system_info_tool.
    2. Identify potential bottlenecks: Inspect resource-heavy processes using resource_usage_tool and list_processes_tool.
    3. Explain findings: Present relevant metrics, suspected causes, and recommended actions.
    4. Request confirmation: Before terminating any process, require explicit approval for the exact PID.
    5. Verify results: Recheck relevant system metrics after an approved action.

    Compatible tools

    Designed for AI agents and development environments that support MCP, including Claude Desktop, Claude Code, and Cursor.

    The skill uses four tools exposed by the MCP-system-info server:

    • system_info_tool
    • resource_usage_tool
    • list_processes_tool
    • terminate_process_tool

    Why use this skill?

    Instead of asking an AI agent to guess why your computer is slow, this skill provides a structured diagnostic workflow using actual system data.

    It prioritizes evidence-based recommendations and includes safety instructions for potentially destructive operations.

    Use cases

    • Investigate slow development environments.
    • Identify applications consuming excessive CPU or memory.
    • Inspect system resources before running demanding tasks.
    • Troubleshoot local development servers.
    • Safely terminate an unresponsive process after user approval.

    Requirements and limitations

    • Requires Python and the MCP-system-info server to be installed separately.
    • Requires an MCP-compatible AI client.
    • Operates on the machine hosting the MCP server.
    • Reports current system information when requested; continuous background monitoring is not included.
    • Process termination is subject to user confirmation and server-side safety restrictions.

    Open-source MCP server: MCP-system-info on GitHub

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.

    Requires MCP-system-info server installation. Limited to the local host machine. Destructive actions require explicit PID-level manual confirmation.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    1 use

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 25 days ago

    • Free with an Agensi account

    Software
    System Info MCPPythonStyle MCPGit

    Permissions

    Read Files
    Write Files
    Network Access
    Terminal / Shell
    Listed25 days ago

    What's inside

    Frequently Asked Questions

    This skill acts as a bridge between your AI agent and your local hardware, allowing the agent to diagnose performance issues, monitor resource usage, and safely manage runaway processes using real-time data instead of guesses.

    You will need an MCP-capable client like Claude Desktop or Cursor and the MCP-system-info server installed on your machine. This skill provides the specialized logic and workflows to orchestrate those tools effectively.

    Safety is a priority; the skill is designed to require explicit user confirmation for a specific Process ID (PID) before any termination command is executed, preventing accidental system shutdowns.

    The skill is currently designed for local host monitoring only; it can monitor remote servers only if the MCP server is running on that remote machine and accessible via a secure tunnel to your local client.

    This purchase includes the optimized agent instructions, diagnostic workflows, and safety protocols required to integrate with the MCP-system-info server; note that the base MCP server itself is a separate open-source dependency.

    New in LLM Ops

    Free