"How to send a message on Slack" matching MCP servers:

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.

MCP server that gives AI agents isolated, named Linux computers with stable IDs and lifecycle control. Supports multiple backends like Docker, Fly Machines, Modal, and E2B, with a dashboard for managing sandboxes.

Runs builds, tests, and benchmarks on a remote compute node via Tailscale and SSH, syncing projects with rsync.

A server that enables LLMs to securely manage and execute commands on remote SSH servers.

Lets Claude manage tmux sessions on Linux — start long-running ML training jobs, check their output, send keystrokes, and kill them.

A collection of Model Context Protocol servers that enable Claude Desktop to provide development assistance capabilities with filesystem, Git, shell command, and web search functionality without incurring API usage costs.

MCP server that gives AI assistants full visibility into your tmux sessions — browse sessions, windows, and panes, read terminal output, and send commands.

Deterministic bash→PowerShell translation layer for AI agents on Windows. Exposes a bash tool over MCP; agents write bash, fauxnix runs it natively on PowerShell 5.1 — no WSL, no VM, no Git Bash required.

An MCP server for driving an ITS session on a PiDP-10 emulator over raw TCP, supporting persistent connections, raw control-byte transmission, and escape syntax for DDT commands. It enables interaction with ITS systems through natural language via MCP tools like open, send, read, and status.

Enables running PowerShell commands on Windows via a single tool, returning raw stdout/stderr and exit code.

Lets AI clients execute shell commands and transfer files on remote machines via configured aliases, while keeping credentials and audit logs local.

Enables AI agents to execute SSH commands, read files, and list directories on remote hosts with a configurable command-safety policy.

Provides transactional intelligence for AI agents, enabling safe tool execution with pre-flight invariant checks, sub-second filesystem snapshots/rollback, causal tracing, belief contradiction detection, and 15 native MCP tools for Claude Code.

Enables web ChatGPT to drive durable, sandboxed Claude Code sessions on a local Mac, with controlled read, modify, verify, and recover operations via six session control tools.

Runs commands on machines you cannot SSH into by publishing steps to a transport the far side already reaches (git, file share, S3, relay), then reads back a log with every line timestamped in UTC. Seven tools cover send, status, logs, stall detection and a pre-flight check.

Provides direct, unsandboxed local machine access via filesystem, Python, Node.js, and shell commands for MCP agents.

Enables AI assistants to execute terminal commands on a host machine with configurable, granular permission controls and safety protections. It features multiple security modes, including allowlists and manual approval, to ensure safe command execution within specified directories.

Local Dev Doctor turns an unfamiliar development checkout into an evidence-backed diagnosis. It discovers how the project is meant to run, checks safe prerequisites, and executes only the exact probe that a user approves.

Bridges Claude to a local OpenClaw gateway on Android via Termux, enabling agent dispatch, observation, control, file operations, and system commands through 10 consolidated tools optimized for the God Orchestrator pattern.

Bridges Claude Desktop to local Windows 10 development environments to enable repository reading, documentation searching, and isolated code execution. It provides a secure interface for running allowlisted terminal commands and scripts directly through natural language.