"How to run desktop commands on a computer" matching MCP servers:

Enables DeepSeek Harness to operate files on another computer over MCP, including browsing, reading, writing, editing, searching, moving, and recoverable deletion, with optional command execution. It supports Windows and macOS via LAN or Tailscale with directory authorization and logs.

Provider-neutral MCP server for managing VirtualBox, VMware Fusion, and VMware Workstation, offering tools for VM lifecycle, configuration, snapshots, guest operations, networking, and artifact resolution.

Enterprise MCP gateway that unifies multiple MCP servers behind one governed endpoint, providing federation, authentication, policy enforcement, caching, rate limiting, and audit.

Enables AI assistants to explore a PostgreSQL database, run bounded read-only SQL, inspect query plans, test hypothetical indexes, find slow queries, and check database health with compact CSV output.

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.

Nido is a local QEMU VM manager. Install it on your computer from https://github.com/Josepavese/nido and run nido mcp via stdio, or use npx -y nido-mcp@latest mcp with QEMU installed locally. It manages VMs on that same computer; a server hosted by Glama cannot access your local VM inventory.

A WorkFlowy MCP Server with node creation, recursive gets, updates, completions, search and replace (with a dry run mode), usage reports, a configurable list of exposed commands and customizable log output.

Enables an AI assistant to operate a Linux machine through tools for files, search, shell commands, long-running processes, git, desktop control, screenshots, and local spreadsheets.

LLM Optimizer is an AI visibility intelligence platform. It analyzes how large language models and AI search engines perceive, cite, and recommend brands; then provides research-backed optimization strategies to improve that visibility.

A self-hosted MCP server that provides capability packs for AI agents to perform browser, desktop, git, and code actions via schema-validated JSON calls, enabling reliable agentic workflows even with small open-weight models.

Connect your Umami Analytics to any MCP client to derive insights from natural language.

Simple MCP Runner makes it effortless to safely expose system commands to language models via a lightweight MCP server—all configurable with a clean, minimal YAML file and zero boilerplate.

Enables AI agents to run curated English and Chinese web searches through a single search_web MCP tool, returning each result with explicit fetched_at timestamps for grounded, provenance-aware answers.

Enables analyzing sales and stock CSV files to identify what to reorder, how much to buy, when products will run out, and how much inventory is tied up in dead stock. Provides read-only inventory checks and CSV column inspection without uploading data.

Enables an agent to query connected MySQL databases through named aliases, running reads immediately while holding data-changing statements for local user approval. Passwords are entered on the user's own computer and never reach the agent.

Enables AI assistants to read, search, organize, and draft email, manage calendar items, and look up contacts through the user's already signed-in classic Outlook desktop app on Windows, with outgoing actions defaulting to drafts for review.

Records how any command-line tool behaves (flags, stdin, outputs, exit codes, edge cases) as golden tests, then diffs a Rust or Go rewrite against the original to prove it behaves the same.

A Model Context Protocol server that enables AI assistants to control Philips Hue smart lighting systems through natural language commands.

Enables AI agents to securely execute terminal commands with persistent sessions, async jobs, and mission control, while providing a live dashboard for human oversight.

A Model Context Protocol (MCP) server that enables LLMs to run ANY code safely in isolated Docker containers.

Easily build MCP tools for Claude desktop app.

The Multi DB MCP Server is a high-performance implementation of the Database Model Context Protocol designed to revolutionize how AI agents interact with databases. Currently supporting MySQL and PostgreSQL databases.

Enables AI agents to work a Noeto kanban board: browse boards and cards, search across them, create and update cards, move and reorder them between columns, comment, and read or write documents and attachments on cards. It runs as a local process for Claude Code and Claude Desktop and deliberately avoids destructive actions such as deleting human-created content.

Enables AI agents to remotely execute shell commands and transfer files on SSH hosts, including jump-host tunneling, background tasks, resumable transfers, and optional approval of destructive commands, while SSH credentials remain in the local process. It runs over stdio or a streamable HTTP daemon and supports auditing, allow/deny lists, and multiple authentication methods.

Give your AI app any GitHub link and the job you want done. UGT gets the project running on your computer and hands you the result.

Give hands to AI. MCP server to run shell commands securely, auditably, and on demand.

Orchestrates distributed research drones on Google Cloud Run, enabling scalable and bidirectional research task management.

ghcli-mcp-connector is an MCP server that lets agents run any GitHub CLI (gh) command—repos, issues, PRs, releases, workflows, gists, and more—as a single static Go binary with a read-only-by-default safety gate on state-changing operations.

An MCP server for prompt and RAG evaluation workflows, enabling users to register, create API keys, and run evaluations via Claude Desktop, Cursor, or other MCP clients, with a hosted backend for heavy evaluation work.

Gives AI coding agents a shared local SonarQube instance plus a SonarQube MCP endpoint per machine, so multiple clients can run scans, wait on quality gates, and read metrics and issues for the auto-detected project in a workspace. Tools also accept an optional server argument to query configured remote SonarQube servers (such as a company CI server) alongside the local one.