命令行 MCP 服务器

Bash for AI agents on Windows via deterministic bash-to-PowerShell translation, without WSL or a VM, with GNU-style output and persistent…

SSH for AI agents: commands, files, backups and health, with approval, a vault and an audit trail

Administers Linux via typed, approval-gated actions with an Ed25519-signed audit trail.

Local shell history and AI agent sessions over MCP: search commands, failures, risk and git changes

SSH connection manager with MCP server for AI-assisted operations across servers.

Manage AWS, Hetzner, OVH and SSH servers: status, logs, CloudWatch, IP bans, safe command exec.

Terminal for AI coding agents: persistent PTY sessions, incremental reads, headless screen capture, multi-agent orchestration and a web…

Interactive PTY sessions over MCP: local shells, SSH, serial ports, and persistent remote sessions.

Launch, screenshot and interact with any TUI app.

Stateful, structured, safe shell sessions for AI agents over local, SSH, and Docker.

SSH & Kubernetes access broker for AI agents; the model never touches a credential.

SSH access with persistent sessions, SFTP and port forwarding, with secrets injected via stdin and redacted from output before reaching…

Command wrapper MCP server for coding agents, compression, workflows, and local automation.

Modern SSH for AI agents — cloud servers to BusyBox routers, with destructive commands blocked.

SSH-based MCP control of remote Linux, macOS, and Windows servers -- 46 purpose-built tools.

Search, retrieve, and diff the full output of past terminal commands recorded locally by backscroll.

Let agents drive vim, htop, lazygit: send keys, wait on screen state, read the rendered cell grid.

Drive tmux locally or over SSH: sessions, windows, panes, keystrokes, pane capture and raw commands, with shared sessions for pair…

Local full-text search over zsh, bash and fish history, with secret redaction and optional capture of cwd, exit code and duration.

Terminal, filesystem and background-job tools for Linux and macOS.

Securely control paired computers with ReMCP.

Inspect, manage and kill local dev servers: see what listens on each port, diagnose port conflicts, find zombie processes and kill by PID…

The WhenLabs developer toolkit — 6 tools, 7 MCP endpoints, one install.

Administer a Linux server: read files and logs, manage systemd services and cron jobs, run read-only MySQL queries, WP-CLI, Git and…

Outbound-only remote shell, detached long-running jobs and temporary file transfer for AI agents, without exposing SSH, ports or a VPN.

Read-only SSH server diagnostics via a fixed 38-command whitelist; secrets redacted, no write path.

The safety gate between AI agents and your servers: typed, policy-checked, audited ops tools.

Run commands on a machine you cannot SSH into. Air-gapped, bastion-only, change-controlled.

Privileged command execution proxy with human approval via pkexec or sudo