More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    ssh mcp

    1

    Securely manage remote servers, execute shell commands, transfer files via SFTP, and open SSH tunnels via MCP.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    ssh mcp

    ssh mcp

    Example session with this skill installed

    Check if nginx is running on the 'production-web' server, then read the config at /etc/nginx/nginx.conf to check for the server_name.

    • Read your context and instructions
    • Compiled the ssh mcp

    I have checked the status of Nginx and retrieved the configuration file from production-web.

    Server Inspection: production-web

    TaskResultDetails
    Service StatusActivenginx.service is active (running) since Tue 2024-05-21.
    Config ReadSuccessFile /etc/nginx/nginx.conf retrieved via SFTP.
    ValidationVerifiednginx -t confirms syntax is currently valid.

    Nginx Configuration snippet

    user www-data;
    worker_processes auto;
    pid /run/nginx.pid;
    include /etc/nginx/modules-enabled/*.conf;
    
    events {
    	worker_connections 768;
    }
    
    http {
    	sendfile on;
    	tcp_nopush on;
    	types_hash_max_size 2048;
    	include /etc/nginx/mime.types;
    	default_type application/octet-stream;
    
    	# Server Name Check
    	server {
    		listen 80;
    		server_name api.example.com;
    		root /var/www/html;
    	}
    }
    

    Next steps

    1. Review the server_name directive to ensure it matches your expected domain.
    2. If changes are needed, I can create a backup and apply a new configuration.
    3. I can check the access logs at /var/log/nginx/access.log if you are seeing traffic issues.

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

    About this skill

    Manage remote infrastructure without leaving your AI agent workflow. This skill provides a secure interface for interacting with remote servers via the SSH MCP server, eliminating the need to manually switch to a terminal for server maintenance, file management, or troubleshooting.

    What it does

    • Remote execution runs shell commands on target hosts with precise timeout controls and output handling.
    • File management creates, reads, renames, and deletes files using SFTP for reliable binary and text transfers.
    • Service tunneling opens local ports to reach private services and databases located behind the remote host.
    • Infrastructure discovery lists available servers and inspects their specific security policies and capabilities.
    • Safety enforcement validates every command against local security rules and system protection settings.

    How it works

    1. Discover the available serverId values and active security policies using ssh_list_servers.
    2. Inspect the remote environment by reading configuration files or checking service statuses with sftp_read_file or ssh_exec.
    3. Execute planned changes, such as updating configs or restarting services, after obtaining explicit user confirmation for write operations.
    4. Verify the success of the operation by inspecting exit codes and re-reading the modified state.

    Frameworks & tools

    SSH MCP server, SFTP, and standard Linux system utilities (systemd, nginx, git).

    Why this beats prompting it yourself

    Generic prompts often fail to handle the stateless nature of SSH calls, leading to broken paths and environment errors. This skill implements a strict safety protocol, including mandatory backups, absolute path enforcement, and automated exit code validation that prevents silent failures.

    Use cases

    • Config management to safely edit and validate Nginx or SSH configurations with automatic backups.
    • Remote debugging to tail logs, check process resource usage, and verify service health across multiple hosts.
    • Database access by opening secure tunnels to reach 127.0.0.1 services on the remote machine.
    • Automated deployments by transferring build artifacts via SFTP and running migration scripts.

    Known limitations

    Does not support interactive terminal prompts, sudo password entry, or background processes like tail -f. Every tool call is stateless and does not preserve environment variables or directory changes.

    No interactive TTY support. No persistence between commands. SFTP or Port Forwarding must be enabled in the server config to use those specific tools. Restricted by local safety net rules.

    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 29 days ago

    Requires

    macOS
    Git
    Windows
    Linux

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files
    Listed29 days ago

    What's inside

    Frequently Asked Questions

    This skill allows your AI agent to execute shell commands, manage files via SFTP, and create secure tunnels on remote servers directly within your workflow, eliminating the need for manual terminal switching.

    To ensure security, the skill does not support interactive prompts or sudo password entry; all commands must be non-interactive or pre-authorized via your server's sudoers configuration.

    Yes, the skill includes a specialized service tunneling feature that allows your agent to open local ports to reach private databases or services hosted behind the remote firewall.

    The skill is compatible with any AI agent or platform that supports the Model Context Protocol (MCP) and has access to the SSH MCP server.

    The skill treats each tool call as stateless, meaning it does not preserve environment variables or directory changes between separate commands; you should use absolute paths for all operations.

    New in APIs & Backend