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

Enables MCP clients to run eight data tools over stdio for product search, ad transparency, company intent, job/ATS lookup, keyword volume, domain SEO, and YouTube transcripts, returning JSON envelopes with item limits, truncation metadata, and structured errors.

Enables an AI agent to reverse-engineer a compiled program with Ghidra — inspecting decompiled code, instructions, callers, memory bytes, and strings — without any source code. Every reply is labelled as fact, computed, or guess, and each claim traces back to hash-checked saved evidence.

Enables researching, verifying, comparing, and composing open-source AI projects with transparent evidence and uncertainty boundaries through read-only tools.

BTC Decision Terminal for AI Agents — live vault-backed Hyperliquid signals, on-chain proof, cross-chain swap. MCP server hosted at https://hypernatt.com/mcp/protocol. 11 tools. Verify in real time.

Enables MCP-compatible coding agents to schedule, check, postpone, and cancel Windows host shutdowns from WSL.

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

We sell open source compliance, scientific, and government data.

A Windows-native MCP server that lets Claude Desktop transcribe audio files locally using whisper.cpp, with no internet connection required.

Enables persistent, project-scoped memory for OpenAI Codex Desktop and CLI on Windows, capturing prompts and responses through managed hooks, with federated recall across projects and optional local graph extraction.

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 comprehensive Windows system management through Claude Desktop, including PowerShell/CMD execution, file operations, archive handling, Git tools, network testing, and system monitoring. Provides a complete toolkit for Windows automation and administration tasks.

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 agents to access real-time Windows PC context including active window, system performance, screen time, productivity analytics, and historical usage through MCP tools.

Enables AI assistants to inspect, diagnose, and manage a local Windows PC through the Model Context Protocol, with 97 tools for task management, cleanup, hardware and security checks, administration, networking, and shell helpers.

Enables AI assistants to locally inspect, diagnose, and manage a Windows PC through 100 tools covering processes, storage, hardware, security, administration, networking, and PowerShell.

A sandboxed terminal on your Mac for Claude chat and Cowork: shell commands, tmux sessions and file edits with no approval dialogs, inside the macOS sandbox (Seatbelt), which blocks ~/.ssh, ~/.aws, the Keychain and startup files. One stdlib Python file, no dependencies, no telemetry.

Search and pull 620+ React and Tailwind sections into your project over MCP.

Enables Claude and ChatGPT to run sandboxed shell commands, manage files and Git, search code, and use system/network tools within a kernel-enforced, per-session workspace jail that blocks access to credentials and files outside the sandbox.

Enables deterministic calculations for AI API and subscription costs, meeting time zones, recurring schedules, and cron next-run previews, returning normalized inputs, units, assumptions, dated sources, and links to results.

Educational tools agent by Birkan Yavuz — an A2A + MCP server for classroom tools, with creator attribution in every result. It offers a catalog of 24 real classroom activities, including math visualizers and reading and sight-word tools.

A Model Context Protocol (MCP) server for the Open Library API that enables AI assistants to search for book information.

Odds are, most of what you want to build is already open source. Tell your AI agent what you're making, and it finds it: which repos to use as they are, which to adapt, and what's left for you to write. Every repo it names is real, licensed for your use or flagged, and checked live.

Check if a flight connection is comfortable, tight or risky, with cited airport data.

Enables validating JSON/JSONC, getting/setting values with jq-like paths, pretty-printing or minifying, validating against Ajv JSON Schema, and diffing local files or inline strings without network calls.

Gives AI assistants read-only, key-free access to Sentinel-2 NDVI time series, ESA WorldCover land-cover shares, and Copernicus 30 m elevation and slope for a point or small area, returning the scene IDs, units, and caveats behind every number. Built-in sanity checks and a verify tool recompute key values through an independent path so the assistant can flag cloudy, low-confidence, or mismatched results instead of guessing.

A high-performance MCP server providing up-to-date documentation for Go, npm, Python, Rust, Docker, Kubernetes, Terraform, and more — fetched from official sources, not training data.

A secure Model Context Protocol server that allows AI models to safely interact with Windows command-line functionality, enabling controlled execution of system commands, project creation, and system information retrieval.

Enables AI agents to control the user's Chrome or Firefox browser, leveraging existing sessions for tasks requiring authentication and user handoff.

Ten tools I built to get facts from official open data, not guesses.

Exposes 55 forensic tools over the Model Context Protocol so agents can query Chilean statutes, jurisprudence, administrative dicta and doctrine from official state sources such as BCN, PJUD, CGR and DT, while running locally for confidential casework. It also supports citation-validated drafting, deadline and docket monitoring, judgment deconstruction, OCR dossier compilation and legal knowledge-graph analysis for civil-law practice, teaching and research.

A Model Context Protocol server that wraps AutoIt functionality, enabling LLMs to automate Windows desktop tasks including mouse/keyboard operations, window management, and UI control interactions.

Open Task Relay provides free, bounded public-good tasks that autonomous AI agents can discover, complete, submit, and independently verify. Its public TypeScript source runs locally with a Cloudflare Workers-compatible runtime and SQLite/D1, exposing MCP over HTTP.

Self-hosted OAM memory with cited recall over your existing deployment. Local stdio adapter with six tools for recall, retaining interactions and documents, operation readiness, stored Profile reads and exact memory removal. Run with npx -y @rocke-dong/oam-mcp; requires Node.js 22 and your OAM user-scoped API key. Submitted by the OAM maintainer with AI assistance.

Enables AI agents to search apparel and tote products, validate artwork at real size, create mockups, get delivered quotes, and place, track, or cancel orders without an account or API key.

Enables agents to control Windows desktop applications through UI Automation and Win32, supporting window management, mouse/keyboard input, element inspection, screenshots, OCR, macro recording, and autonomous multi-app missions. It also provides an HTTP/stdio MCP interface, an operator UI, and optional telemetry and safety controls.

Enables AI agents to query multi-cloud costs, inventory, waste, and commitments across AWS, GCP, Cloudflare, and OVH through read-only MCP tools.

Local-first code retrieval MCP server: hybrid semantic + keyword search over an AST-aware index of your codebase, with symbol definition and reference lookup, repo maps, and file tools. Runs fully offline; serves Claude Code, Cursor, and any MCP client over stdio or HTTP.

Enables secure, self-hosted audio transcription through a single MCP interface, letting users route recordings from authorized sources to Microsoft MAI, ElevenLabs Scribe, or Groq Whisper and receive a consistent transcript schema.

Make posters, social posts, slides and landing pages in the coding agent or chat you already use (Copilot, Claude, Codex, Cursor), with 198 design systems, checks and PDF/PNG/PowerPoint export.

MCP tool server that gives any AI agent the ability to search, scrape, and analyze content across the internet.