Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Linux SSH Remote Administration Pro

    1

    Provide your AI assistant with direct, secure, and authenticated shell access to remote Linux servers and cloud VMs across 62 specialized administrative tools.

    $19

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Linux SSH Remote Administration Pro

    Linux SSH Remote Administration Pro

    Example session with this skill installed

    Connect to the production-web session, check for containers using more than 1GB of RAM, and show me the last 50 lines of logs for the heaviest one.

    • Read your context and instructions
    • Compiled the linux ssh remote

    I have connected to the production-web session and analyzed the resource utilization of all running containers.

    Container Resource Audit

    Container NameCPU UsageMemory UsageStatusImage
    api-gateway-112.4%1.42 GBUp 4 daysnginx:alpine
    worker-proc-345.2%840 MBUp 12 hourscustom-worker:v2.1
    redis-cache2.1%120 MBUp 4 daysredis:7-bolt
    db-replica5.8%910 MBUp 4 dayspostgres:15

    The api-gateway-1 container is currently exceeding the 1GB threshold.

    Tail Logs: api-gateway-1 (Last 50 Lines)

    2023/10/27 14:22:01 [error] 31#31: *442 upstream timed out (110: Connection timed out) while connecting to upstream, client: 192.168.1.45
    2023/10/27 14:22:05 [warn] 31#31: *445 1024 worker_connections are not enough while connecting to upstream
    2023/10/27 14:22:10 [info] 31#31: *450 client 10.0.5.12 closed keepalive connection
    2023/10/27 14:22:15 [error] 31#31: *452 worker_connections are not enough (possibly a leak in upstream socket handling)
    2023/10/27 14:23:44 [crit] 31#31: *501 accept4() failed (24: Too many open files)
    ... [remaining 45 lines of logs showing socket exhaustion] ...
    

    Next steps

    1. Use ssh_docker_inspect(container="api-gateway-1") to check current ulimit settings.
    2. Use ssh_docker_compose(action="restart", path="/etc/deploy") to cycle the gateway and clear leaked connections.
    3. Run ssh_system_load() to ensure the host is not under broader resource pressure.

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

    About this skill

    🚀 Production Workflows

    1. Zero-Downtime Host Health Audits: Evaluates CPU load average, RAM/swap, filesystem disk space, and inode exhaustion in real time.
    2. journalctl & systemd Crash Triage: Investigates failing systemd daemons, queries service statuses, and searches system logs for OOM-killer events.
    3. Socket & Network Boundary Diagnostics: Inspects active listening ports (ss), tests TCP boundaries, and verifies upstream DNS resolution.
    4. Remote Docker Fleet & Compose Management: Lists container resource stats, executes diagnostic commands inside sandboxes, and restarts multi-container stacks.
    5. Confirmation-Gated Service Restarts & File Edits: Performs safe configuration substitutions with automated backups (sed_replace) and cycles system daemons.

    🛡️ Safety & Governance

    • Read-only autonomous metrics, file reading, log searching, and container stats.
    • Confirmation-gated arbitrary command execution, file modifications, service restarts, and process kills.

    Launch via: uvx linux-ssh-mcp

    Requires pre-configured SSH environment variables or stored credentials. Verification script must be run before first use. High-impact commands like ssh_delete require specific path inputs.

    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 any payment.

    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

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 16 days ago

    Requires

    Python
    Linux Ssh MCP
    uv (Python tool runner)
    Observability MCP

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Environment Variables
    Listed16 days ago

    What's inside

    Frequently Asked Questions

    This skill provides a structured interface of 62 tools that handle complex shell escaping, stateful session management, and precise syntax for operations like in-place file editing, which generic AI prompts often struggle to execute reliably.

    The skill is compatible with any AI agent or platform that supports the Model Context Protocol (MCP), such as Claude Desktop or other MCP-enabled IDEs, and it connects to any standard Linux environment via SSH.

    Setup involves configuring your SSH environment variables or using the included `ssh_save_credentials` tool; you must also run the provided verification script to ensure your remote host is reachable and permissions are correct.

    Yes, you can manage the entire lifecycle of Docker containers and Docker Compose stacks, including pulling images, streaming real-time statistics, and inspecting container logs directly through the agent.

    The server includes a suite of security auditing tools to review login history, identify failed authentication attempts, check cron persistence, and search system logs for suspicious activity.

    You receive the full MCP server package containing all 62 specialized tools, the necessary configuration files, and a verification script to validate your connection before you begin administration tasks.

    New in DevOps & Cloud