"MCP servers that don't require API keys" matching MCP servers:

Parse, validate, and explain cron expressions with pay-per-call via x402 (USDC on Base L2), returning next run times in any timezone.

MCP server for macOS desktop automation enabling screenshot, click, type, scroll, and more. Retina-aware, supports CJK text input and multi-monitor, works with any MCP client without API keys.

MCP server that lets an AI assistant see and control an Android phone over ADB: screenshots, UI dump, tap, swipe, type, keys, open apps. Safety guards: device allowlist, sensitive-app block, raw shell off by default, rate limit.

Enables AI agents to operate Windows computers with parallel, human-like input streams, including held keys, concurrent mouse/keyboard actions, UIA/OCR targeting, and a knowledge base for engineering software.

Enables agentic control of Windows via MCP tools for screenshots, mouse, keyboard, UI Automation, OCR, windows, and clipboard, while risky actions require real-human approval through a policy-gated dialog with audit logging.

Enables an OAuth-capable AI assistant to manage a self-hosted Linux server, starting with host-health and probe snapshots and optionally expanding to shell commands, bounded text-file reads/writes/moves, and asynchronous jobs through an owner-authenticated local broker. Configuration and credentials stay private on your own machine, with no hosted service or model API keys required.

An MCP server that gives AI agents real OS-level control of macOS, enabling them to click real buttons, type real keys, and observe rendered screens just like a human would.

Enables an AI agent to open a real Konsole window on KDE Plasma 6 / Wayland, type commands directly into its pseudo-terminal, read output and exit codes, send special keys, and manage interactive programs. It also brings that window to the foreground and captures the desktop with the system's own Spectacle, returning the screenshot image in the tool response.

MCP server that provides computer control capabilities including mouse movements, keyboard actions, screenshot capture with OCR, and window management through a unified API.

MCP server that wraps the MSPbots Fleet Platform API, enabling host inventory management, on-demand script execution, and saved osquery queries over the Model Context Protocol.

Enables AI clients to query and manage Aagon ACMP data in natural language through the Public API, covering clients, containers, jobs, tickets, assets, inventory and vulnerabilities. Read actions run immediately, while write, execute and delete actions require one or two people to approve them on a web page before they reach ACMP.

Enables driving macOS apps from Claude Code — screenshots, accessibility trees, clicks, typing and keys — by borrowing the Computer Use eyes and hands from OpenAI's ChatGPT/Codex desktop app, with persistent JavaScript scripting, text-targeted batching, diff output and macros that collapse many actions into one call without consuming Codex quota or calling a model.

Enables AI clients to operate remote VPS hosts through a jump-host gateway with a fixed whitelist of tools, allowing them to read logs, inspect and edit configuration files, manage services, and deploy or roll back versions. Production writes require a per-client time-limited lease, and all actions are audited, verified, and automatically reverted on failure.

A thin MCP adapter that connects an LLM to the ros2_medkit SOVD HTTP API, enabling discovery, data retrieval, operation execution, and configuration management for ROS 2 systems.

Enables managing local tmux sessions, windows, and panes over stdio, including listing, creating, renaming, killing, sending keys, and capturing pane output.

Enables MCP clients to control macOS via accessibility and screen recording, providing tools to list apps, observe UI, click, type, press keys, and scroll.

Enables inspecting local listening ports, process owners, Docker mappings, and local LLM signatures, plus looking up or terminating the process that owns a specific port when write access is allowed. Mutating actions require confirmation and are blocked in dry-run mode.

Enables an AI agent to perform real dev VM work—such as checking git status, switching branches, tailing logs, and restarting services—through typed operations that are re-validated and sandboxed by a daemon and require human approval before execution.

Enables AI agents to read and write Elgato Stream Deck desktop profile manifests, generate icons, wrap shell commands in script-backed keys, and restart the app so edits take effect. It runs either locally over stdio or remotely over a bearer-token-gated Streamable HTTP transport that adds a health-check tool.

A Windows computer-control MCP server for the DeepSeek Harness plugin that lets an agent take screenshots, magnify the view for low-vision assistance, move and click the mouse, type and press keys, enumerate and focus windows, and switch input methods. It also bridges to Krita to drive drawing, pressure-curve, liquify, smudge, and brush operations.