"Best open-source NPX or UVX tools for terminal deployment on Windows" matching MCP servers:

Enables MCP-capable agents to control a real QEMU virtual machine through nine computer-use tools—screenshot, click, move, type, key, scroll, status, start, and stop—without accessing the host’s pointer, clipboard, or files.

Enables AI agents to query OpenRouter model information including prices, ELO rankings, context, and perform comparisons.

A Windows-optimized server providing universal data analytics for JSON and CSV files through over 32 tools including schema discovery and interactive visualizations. It is specifically designed for seamless integration with Claude Desktop on Windows.

A simple demonstration MCP server that provides a sum_numbers tool for calculating the sum of a list of integers, built using the FastMCP framework.

Provides secure file read, write, and edit operations for Windows, with enterprise-grade features like atomic writes, file locking, and path validation.

Enables MCP agents to inspect deployment knowledge extracted from a repository, covering workflows, services, deployments, and images.

An MCP server that lets an AI agent use a real terminal the way a person does: type, press keys, click, read the screen, take a screenshot.

Enables analyzing Salesforce deployment logs, validating metadata manifests, assessing permission risks, and generating remediation plans through deterministic, local-only rules.

Fill standard legal agreement templates (NDAs, SAFEs, NVCA docs, employment, cloud terms) and produce DOCX files.

A Model Context Protocol (MCP) server for producing better Terraform through CLI analysis (tflint, checkov, trivy, kics, infracost), best-practice guidance from terraform-best-practices.com, cloud provider recommendations (Azure, AWS, GCP), and Terraform Registry resource and module guidance.

An MCP server designed for managing files and folders specifically on the Windows Desktop. It enables users to perform file operations like deletion while implementing security measures to prevent path traversal outside the Desktop directory.

A demonstration MCP server that provides a simple addition tool for learning how to create and deploy servers following the Model-Context-Protocol specification. Serves as a basic example for developers getting started with MCP server development.

An MCP server providing stock market data and trading capabilities through multiple broker APIs including Robinhood and Schwab.

A VSCode and Cursor extension that captures real-time terminal output and exposes it to AI assistants via the Model Context Protocol. It enables agents to proactively monitor logs, command execution, and errors without requiring manual copy-pasting from the user.

Enables Claude Code to diagnose Windows slowdowns from captured evidence and perform explicit, policy-checked, verified repairs such as terminating exact processes, clearing ports, or restarting Explorer, with audit logging and local-only data.

Enables agents to create and control real pseudo-terminal sessions: run commands with exact output and exit codes, stream long-running process output, type into interactive programs, monitor session state, and terminate whole process trees.

MCP server that captures a Windows application's pixels and bounded UI Automation tree with provider-exposed text for Codex inspection. It supports capture, listing, retrieval, and watcher control commands.

Provides Python and FastAPI coding best practices with searchable guidelines, code review capabilities, and actionable improvement suggestions with examples across general coding, performance, and code quality categories.

Local-first memory layer for AI coding agents — Markdown as source of truth, MCP server + CLI, human-reviewed capture, team knowledge via git PRs

Developers: Search your zsh, bash, or fish shell history from Claude Code, Cline, Cursor, Zed, or any MCP client using tools like search_history (full-text with timestamp/CWD/exit code), recent_in_dir, failed_commands, and command_chains for multi-step sequences. Reindex after new activity. Local-only SQLite FTS5 with secrets redacted before storage.

Enables AI agents to drive genuine interactive Windows console sessions through ConPTY, so they can launch PowerShell, pwsh or CMD, send keystrokes, answer prompts, watch rendered screens and block until output matches. Multiple persistent shells can run in parallel, supporting live input, incremental reads, interrupts and window resizing.

Enables AI models to run interactive tmux terminal sessions that a human can watch and type into, with all output logged and split into searchable per-command regions so only needed lines enter context. Also guides models through unfamiliar tools by returning exit statuses and key output alongside advice on the tool being used.

Open Kioku is the local-first code intelligence and evidence layer for AI coding agents (Claude, Cursor, Codex, Zed, and other MCP clients). Instead of letting agents blindly crawl files, guess blast radius, or read the entire repository repeatedly, Open Kioku gives them a precise, pre-indexed code index to build evidence-backed plans before they edit, and verify boundary limits after they edit.

Enables running example MCP servers over both stdio and streamable HTTP transports, providing tools for integer addition, streaming progress counts, and greetings, and can be installed directly from GitHub via uvx.

Enables AI assistants to keep Rojo serving and auto-connected for Roblox Studio projects and to import FBX, OBJ, GLB, or GLTF models through Studio's own 3D Importer on Windows.

Enables secure Windows development automation by providing MCP tools for filesystem access, project builds, restricted PowerShell commands, and approved network fetches.

Enables two or more Claude Code terminals on the same machine to communicate by registering and sending messages via the local filesystem.

Enables Claude Desktop to read terminal command output by capturing commands prefixed with 'cap' to a log file. Eliminates the need to copy-paste terminal errors and output when asking Claude for help.

An MCP server for creating and managing shared terminal progress bars from AI agents, enabling real-time tracking of parallel tasks.

An MCP server that enables Claude to access Windows screenshots from WSL2, allowing users to easily share screenshots with Claude Code without manually navigating complex file paths.

A production-grade MCP server for Windows developer environments, providing AI assistants with secure terminal, filesystem, git, Docker, SQLite, browser, and GitHub capabilities through 12 providers and 40+ tools.

Enables AI development tools on Windows to send native system notifications for task completion, errors, and reminders, with customizable icons and sounds.

Local + remote terminal interaction control MCP Server. Lets AI agents control interactive TUI programs the way a human would.

Analyzes source code dependencies across multiple programming languages in the specified directory to identify file relationships, assisting in dependency management and project structure understanding.

A template for deploying an MCP server on Vercel, with example tools like roll_dice and get_weather.

A Windows-only MCP server that gives AI models eyes and hands on a Windows machine, enabling file reading, screenshots, mouse/keyboard injection, and an auto-debug loop with a safety-focused watchdog for protected abort regions.

An enterprise-grade automation server that enables AI assistants to control Windows PCs through intelligent UI element detection, window management, and system-level commands. It leverages the Windows UI Automation tree for reliable interaction, providing tools for mouse/keyboard control, application management, and high-performance screen state analysis.

Enables running a stateless Model Context Protocol server over Streamable HTTP on Cloudflare Workers or any fetch-capable runtime, with signed sessions, origin checks, and JSON-RPC request handling. It lets developers define tools with JSON Schema validation and per-request context.

Enables Claude Code, Cursor, and Codex users to orchestrate plan/build/review workflows across host or CLI models with a spec gate, tool vetting, hard per-run and per-day cost/token limits, safe defaults, and clear logs.

An MCP server that enables AI assistants to navigate, search, and analyze local Keycloak source code to support developer customizations like SPIs and authenticators. It provides tools for searching classes, generating boilerplate code, detecting breaking changes between versions, and tracing dependencies.