"Deploying an MCP service in an offline environment" matching MCP servers:

Enables Codex to manage a local Claude Code companion through MCP, implementing a dual-agent workflow where Codex handles reasoning and review while Claude Code performs engineering tasks.

Provides agents with real Linux VMs to run commands, manage files, expose ports, and track costs, all through an ephemeral sandbox service.

Enables AI agents to manage a Canonical Landscape estate, including inventory, alerts, patching, and script execution, with built-in safety layers to prevent accidental destructive actions.

An MCP (Multi-Agent Conversation Protocol) server that enables interaction with Google's Managed Service for Microsoft Active Directory through its OpenAPI, allowing users to manage identity resources through natural language.

An MCP server that connects to existing IPython kernels, allowing Claude to execute code in a shared persistent environment with your IDE.

A single-purpose MCP server that lets an AI assistant run commands over SSH on a fixed, pre-configured host only, with an explicit per-call confirmation gate before execution.

A persistent Python REPL MCP server for AI agents with stateful execution, real timeouts, crash isolation, and an MCP bridge to call other tools in the project.

An open MCP server that gives any AI agent SSH access to remote Linux/Unix machines — shell commands, file read/write, and SFTP transfers.

An MCP server for Hyprland that enables AI agents to control workspaces, windows, mouse, keyboard, and take screenshots on a Wayland desktop.

Self-hostable remote terminal assistance over MCP. Agents create one-command connection invitations, execute commands, and manage interactive sessions on user-authorized macOS, Linux, and Windows computers without requiring an SSH daemon.

An MCP server that gives coding agents hands and eyes on an Android device, providing 19 tools for building, testing, installing, UI inspection, input, logs, and toolchain diagnosis. It returns concise, structured results to make the build-debug loop efficient.

Enables agents to verify completion by cold-running an acceptance command and reporting whether it exits with code 0, returning a pass/fail receipt with output and refusal reasons.

Exposes the official lark-cli as an MCP server, enabling agents to execute arbitrary CLI commands, query API schemas, and manage authentication.

Provides the current date in multiple formats (e.g., European, ISO, US) via a simple MCP tool.

Enables an AI assistant to read and control your real, logged-in Safari browser tabs, with a local model gating every write action for safety.

Exposes persistent, stateful remote Bash sessions to AI agents via SSH, enabling command execution with preserved working directory and environment.

An MCP server that lets AI agents list sessions, read terminal screens, type commands, and run commands (with optional waiting for exit status) in Rex terminal blocks on the local machine through the rex CLI. It exposes a single allowlisted passthrough CLI tool plus a guide tool, deliberately excluding destructive or cross-host operations.

MCP server that turns Kimi K2.6 Turbo into an agentic coding assistant with tools for file operations, shell commands, and code search.

Offline server that explains any shell command token-by-token and flags destructive ones (rm -rf /, curl | sudo bash, dd/mkfs/shred to a disk device, chmod -R 777 /) — a safety gate for agentic shell execution.

Enables MCP-compatible AI clients to securely monitor and manage a self-hosted Linux VPS over SSH, including service status, disk and RAM usage, TLS certificate expiry, fail2ban summaries, and two-step confirmed service restarts or IP unbans.