"Exploring Computer Usage" matching MCP servers:

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.

MCP server for querying OpenAI usage and cost data, including spend summaries, daily breakdowns, month-over-month comparisons, and token usage by model.

Enables AI agents to drive a Linux/X11 desktop via AT-SPI accessibility-tree perception and element-level actions, avoiding screenshots and coordinate clicking.

Provides safe Linux desktop automation for Codex through focused MCP tools for inspecting, clicking, typing, dragging, and verifying native applications on Wayland and X11.

A Local Computer Vision Engine for Photo Libraries

A local-first, multi-provider cost meter for LLM usage, exposed as MCP tools. Captures every call into a local SQLite ledger and lets any coding agent query spend, compare providers, and get recommendations — no cloud, no account. First-class support for Chinese providers (Qwen, DeepSeek) alongside Anthropic and OpenAI.

Enables low-cost agent models to control Windows applications through a compact, state-safe proxy over Open Computer Use, reducing model-visible context by up to 99.8% with support for record/replay and reusable UI component memory.

Provides full access to a local Windows computer via MCP, enabling arbitrary command execution, file operations, and process management through a secure stdio or HTTP tunnel.

A MCP server for tracking AI usage metrics and structured logs across applications. Monitor model calls, analyze usage patterns, track costs, and debug AI interactions.

Enables MCP agents to automate real GUI applications on headless desktops, providing background mouse/keyboard control, window/process management, screenshots, and safe human handoff without disturbing the user's desktop.

Enables an agent to see and operate a GNOME Wayland desktop like a human, including screenshots, mouse/keyboard control, accessibility tree access, OCR, clipboard, and audio listening.

A Python MCP server that provides unified access to satellite and geospatial data through natural language queries, with automatic place name geocoding and support for raster, vector, and Zarr formats.

Provides a persistent Docker computer with terminal, file editing, and optional desktop GUI control through a Three.js interface.

This server enables AI agents to operate Windows and Linux computers by observing the screen, understanding the UI through accessibility, OCR, and vision, and performing mouse, keyboard, window, clipboard, and system actions with verification and recovery.

A low-level computer-use MCP server that exposes raw desktop control (mouse, keyboard, shell, windows, processes, screenshots, etc.) to MCP clients like Claude Code and Codex.

A read-only DuckDB MCP server offering context-efficient analytics tools (list_datasets, describe_table, profile_column, explain, query) with a semantic layer for business rules, security guards, and disclosed truncation to help LLMs produce correct answers while minimizing token usage.

Provides cryptographically signed, tamper-evident compute usage receipts via a Model Context Protocol server, exposing tools to record usage, verify receipts, list the ledger, and verify ledger integrity without requiring any account, API key, or single cloud provider.

MCP server that lets AI agents route web requests through NodeMaven residential and mobile proxies, with tools for geo-targeted fetching, proxy checking, and location/usage queries.

Fail-closed evidence manifests for financial AI research: one manifest records evidence artifacts, cutoff timestamps, checks, AI usage and human approval — one verdict before anything ships. MCP tools: gov_check, gov_report, gov_init.

MCP server for RapidOddsAPI that provides bookmaker odds, live scores, arbitrage and value bets to AI assistants. It supports querying sports, odds, results, and betting opportunities with credit-based usage.