"A semantic web search for 'Exa'" matching MCP servers:

Enables an AI agent to operate a spare Android phone through MCP: capture screenshots, inspect UI controls, tap/swipe, input Chinese text, launch apps, and optionally run rooted shell commands or transfer files. It also supports a live web console for remote viewing and control.

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

Enables AI tools to open the macOS Maps app and search for places or addresses through a single MCP tool, without requiring a Maps API key.

Lightweight MCP server that exposes tools for system information and weather lookup, designed for agent integration via stdio.

Enables AI assistants to read iMessage history and send messages on macOS. Supports conversation listing, message search with keyword and semantic modes, contact lookup, and sending messages to existing conversations.

Enables access to and searching of browser history from major browsers (Brave, Chrome, Firefox, Safari, Edge, Arc, Opera, DuckDuckGo) to personalize LLM interactions and retrieve past browsing data through natural language queries.

A small MCP server that wraps MoneyMoney on macOS via AppleScript, exporting account lists and transactions (bookingDate, amount, name, purpose) as plists for invoice reconciliation, complementing a companion Apple Mail server.

Enables voice-controlled hardware to execute approved Mac actions (like opening apps and querying system status) through a secure MCP bridge.

Lets Claude Desktop and Claude Code inspect and drive Windows desktop applications in the background, including clicking, typing, launching, and verifying results, while the user keeps their mouse, keyboard, and foreground window.

MCP server for controlling Android devices via semantic actions with verification, enabling any MCP client to interact with phones through natural language and structured tools.

A comprehensive MCP server that enables AI models to perform local file operations, command execution, and task management across multiple platforms. It features advanced capabilities like row-level file editing, directory searching, and system monitoring with built-in security filters.

An MCP server that enables secure terminal command execution, directory navigation, and file system operations through a standardized interface for LLMs.

Pre-alpha P2P remote-control app with a local stdio MCP bridge for paired computers. Users build from source; platform support and host-side approvals apply.

Windows computer use in the background for Antigravity and Gemini: look at a window, then act in one verified batch with targets named by their label, without taking the user's mouse, keyboard or foreground; irreversible actions need explicit confirmation.

Enables AI to remotely control macOS systems via VNC with full desktop capabilities including screenshots, mouse control, keyboard input, and application management. Includes a web-based chat interface for natural language control.

Fast file search across Windows (Everything SDK), macOS (Spotlight/mdfind) and Linux (locate/plocate). Single search tool with platform-specific filters, sorting and an optional configurable tool name.

Enables any MCP-compatible AI, whether in the browser or running locally, to create and edit projects, run terminal commands and long-running jobs, and optionally use Docker, all guarded by a policy engine, workspace jail, authentication, and audit logging.

A comprehensive MCP server for Frida dynamic instrumentation, enabling AI agents to manage devices, processes, scripts, memory, and ADB operations.

This server provides a privacy-focused meta search capability by integrating multiple search engines without tracking or user profiling, supporting various categories and languages for filtered searches.

Enables AI models to play the game Peggle by capturing the primary monitor's screen and simulating mouse clicks. It provides tools for visual analysis and coordinate-based interaction to automate gameplay.

Local AI ops broker that keeps SSH secrets on your machine, exposes intent-level MCP tools to agents, and requires approval via a loopback Web UI for dangerous writes.

Enables AI agents to control Android TVs, TV boxes, phones, and tablets over ADB through MCP tools for scanning and connecting devices, pressing keys, launching apps, opening URLs, searching YouTube, setting alarms and timers, managing volume and power, checking state, and capturing screenshots.

Gives an LLM agent control of the macOS desktop from a single self-contained Rust binary: Set-of-Mark numbered screenshots, Accessibility-tree clicks with browser-JS fallback for web content, Apple Vision OCR, mouse, keyboard, and clipboard.

A simple MCP server that provides waiting functionality to pause until other tasks finish, with progress reporting and support for CLI or HTTP server with SSE.

Enables agent-native desktop control by driving mouse, keyboard, and interface elements through accessibility-first semantic operations, with fallback to screen coordinates when accessibility cannot reach a target.

Provides an experimental semantic interface for discovering and reading mock systemd unit resources for service and timer units, with tools for listing supported unit types and units.

Aggregates multiple local stdio MCP services into a single HTTP endpoint and launcher-managed local processes, with a mobile-first web console for starting, stopping, monitoring logs, health checks, and usage.

Bridges AI assistants to Linux D-Bus for system interaction, enabling clipboard, notifications, screenshots, and service discovery with configurable security levels.

Lets an agent install, control, and repair dsh web as a Windows service so it auto-starts at boot, runs without a console window, and survives sign-out — covering service status, install/uninstall, start/stop/restart, and a side-effect-free install preview. It also tails service logs and translates them into plain-language diagnoses with fixes for failures like port conflicts, incompatible profile plugins, and plugin trees that fail to load.

Connects ChatGPT Web to a self-hosted local coding workbench, enabling file editing, shell commands, Git/GitHub operations, multi-workspace management, code review, terminal processes, checkpoints, and optional Docker sandboxing.