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

A lightweight server that enables AI agents to interact with the Windows operating system, allowing for file navigation, application control, UI interaction, and QA testing through various tools.

Routes every Claude Code/Hermes prompt through a local LLM planner and Open-Jev probe, injecting calibrated probability context while failing open if local services are unavailable.

Enables ChatGPT to control multiple registered Windows devices through a self-hosted gateway, routing Desktop Commander tool calls to specific workers by device ID.

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.

Provides Dify apps with a secure, app-scoped MCP tool catalog and action gateway for authorized FlowFlox operations, enabling intent-driven planning and fixed operational processes without exposing global credentials.

Enables web ChatGPT to drive durable, sandboxed Claude Code sessions on a local Mac, with controlled read, modify, verify, and recover operations via six session control tools.

Enables Claude to delegate web search, page reading, text drafting, and parallel multi-model image generation to cheaper helper models on any OpenAI-compatible backend. Claude stays in charge of planning and final decisions while consuming fewer of its own tokens.

Connects Claude Code and Codex to Jev-compatible System One services for context compaction, completion verification, and decision tasks like screening, classification, and gating.

Enables multiple MCP agents to read and write a single user-controlled, local-first fact layer under one user identity with explicit scopes, preserving sources, versions, permissions, and audit history. Supports structured memories such as preferences, facts, task state, and decisions, plus structured handoff capsules so one agent can resume another's work by task ID.

Enables ZCode to control a real Chrome browser, including tabs, navigation, page content, clicks, form filling, keyboard input, scrolling, screenshots, and JavaScript evaluation through a local MCP bridge.

Enables ChatGPT to invoke native OpenClaw browser operations directly through an MCP connection, forwarding actions to the local Gateway while preserving runtime errors and providing a local call monitor.

Persistence, headed Chromium browser control for MCP clients like OpenCode and Claude Code, enabling navigation, inspection, clicking, filling, and human-gated actions on JavaScript-heavy or login-walled pages.

Enables AI agents and IDEs to discover, install, and execute skills over Model Context Protocol via stdio or SSE, with semantic search and framework bridges.

A passive MCP server that exposes a toolbox of executable tools (shell, network, HTTP, AI search, SSH, S3 file operations) to autonomous agents via Streamable HTTP, with strong security features including Docker sandboxing and WAF.

Enables OpenAI-compatible clients to access external tools, APIs, repositories, and data sources through MCP with allowlisting, approval, and argument validation, deployable as a FastAPI service or Python library.

Transforms any API into an intelligent MCP agent in seconds, enabling natural language interaction with APIs through the Model Context Protocol.

Enables AI agents to control Chrome, Edge, Brave and other Chromium browsers through an extension and native messaging host, exposing a Claude-in-Chrome-compatible tool set for real clicks, typing, screenshots, accessibility-tree reading, page text, form filling, JavaScript execution, console and network inspection, file uploads and GIF recording. Agent sessions run in isolated tab groups with per-site permission prompts, activity logging and a global stop control.

An MCP (Model Context Protocol) server implementation using HTTP SSE (Server-Sent Events) connections with built-in utility tools including echo, time, calculator, and weather query functionality.

Enables ESP32 XiaoZhi voice devices to command a Windows PC via MCP, including app control, file operations, screen vision, browser interaction, shell execution, and orchestration of local AI coding agents like Codex CLI and Claude Code.

An Omni Agent MCP server that provides AI models with 8 external tools for real-time data retrieval, Wikipedia search, and arithmetic operations, designed for deployment on Google Cloud Run and integration with Gemini Enterprise via Vertex AI Extensions.

Enables AI agents to control a live Blender session through the Model Context Protocol, including scene and object manipulation, rendering, PolyHaven asset access, and runtime switching between multiple LLM backends.

Unified AI Agent SaaS Connector & Multi-Provider Gateway connecting to 1,000+ SaaS platforms, vector databases, and 500+ LLM models via MCP, REST API, and CLI.

A Python-based MCP server that provides coordinate conversion between latitude/longitude and UTM/TWD97, along with various civil engineering calculation tools for LLM and AI application integration.

Instant web hosting for AI agents. Publish a live site in one call, no account needed.

An MCP server that exposes 43 domain tools behind 4 meta-tools, applying guardrails such as budgets, rate limits, schema validation, human-in-the-loop confirmation for mutations, PII redaction, and an append-only audit log while reducing context window usage.

Sub-15ms edge intelligence tools for Claude Desktop, Cursor, and LLM agent loops. Provides sub-millisecond LLM JSON repair, web-to-markdown token compression (cuts context tokens up to 90%), PII redaction, and RFC 5322 B2B email deliverability verification at zero marginal token cost.

A registry that enables MCP clients to discover and install MCP servers.

A production-grade MCP server that provides a centralized microservice toolkit for LLM agents, enabling web search and extensible tool integration.

A meta-MCP server that orchestrates tools from multiple MCP servers, enabling complex Python workflows with loops and conditionals.

MCP server that gives AI coding agents (Claude Code, Cursor, Cline, etc.) access to multiple AI models through Antigravity CLI and OpenAI Codex CLI, enabling mid-conversation model consultation and code review.

Exposes OpenClaw tools (web search, page fetching, browser automation, PDF analysis, messaging, inter-agent communication, Canvas) as MCP tools for ACP agents.

Enables AI agents to drive real Google Chrome with stealth and captcha handling, using Patchright to avoid bot detection.

Enables building, optimizing, reviewing, and running AI agents and skills, plus managing authorized work items, in Erstan's QA environment via OAuth-authenticated MCP.

A deterministic MCP tool-list relay that lets operators filter tools by include/exclude rules and exposes a filtered stdio MCP server to local clients.

lark-tools-mcp connects Lark and cursor. It provides cursor with the ability to read documents, send messages, process tasks, and perform data analysis.

Enables MCP-compatible agents to discover and call x402 paid services from a directory of over 2,000 APIs.

Remote-first, model-independent Windows execution MCP for ChatGPT, Claude, Gemini, and other MCP-compatible AI clients.

Persistent MCP server runtime for progressively discovering and loading MCP, REST, and local CLI adapters, with host-side credentials and explicit confirmation for mutations.

Enables ChatGPT Web to discover and invoke native local Codex tools via OpenAI's Secure MCP Tunnel, with the local host executing commands and returning results.