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

Starts shared local Streamable HTTP endpoints for Premiere Pro, After Effects, and Lightroom Classic when those apps launch, letting multiple MCP clients use the open Adobe documents.

An MCP server that provides access to the Midjourney Best Experience API for generating and manipulating images. It enables users to execute prompts and perform actions like upscaling, variations, and zooming directly within MCP-compatible applications.

Enables executing shell commands and rendering their ANSI-colored output as styled PNG terminal screenshots with selectable themes, window chrome, watermarks, and timestamps. Useful for pentest reports, documentation, and professional terminal captures.

Enables AI agents to drive a user's own signed-in Google NotebookLM (Gemini Notebook) account through 51 MCP tools, covering notebook and source management, grounded chat with numbered citations, fast and deep research, and generating or downloading audio/video overviews, slide decks, quizzes, flashcards, mind maps, infographics, reports and data tables. It runs over stdio or streamable HTTP on localhost and sends progress notifications for long-running jobs.

Enables agents to compress JPEG, PNG, and WebP images to a target byte size, split PDFs by page or ranges, and remove image metadata while processing local files without sending file bytes over the network.

Enables vision-capable AI clients to read and adjust Capture One on Windows through an MCP stdio server (plus a JSON CLI), applying exposure, curves, color, layer and mask edits and returning real Capture One-rendered previews. It runs a local bridge to C1's native parameters with no presets, screenshots or synthetic input.

Enables recognition and extraction of architectural CAD drawings (DWG) by creating tasks and retrieving structured results for frames, title blocks, and 23 building component types, including rooms, doors, windows, stairs, and text.

An MCP server for controlling Adobe Photoshop from AI assistants, with Windows-first workflow, structured state, smoke-tested action playback, and a bundled Codex skill for image editing.

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 small models to turn a short brief into complete HTML pages or looping GIFs with typography, palette, borders, motion, and validation already decided. It also lets agents list styles, retrieve style rules, create assets, validate HTML, and access reference examples.

Enables agents to commission and refine web pages, product prototypes, landing pages, decks, images, and motion through the desktop app, and to read design files, copy artifacts, and access design systems.

Enables assistants to publish readable replies and status updates to e-ink displays and Home Assistant, with switchable characters and state retrieval through MCP tools.

Enables MCP agents to generate open-weight videos through Amazon Bedrock AgentCore Gateway tools, with job polling, safety screening, provenance manifests, tenant isolation, and GPU cost reporting on scale-to-zero spot instances.

Zero-dependency MCP server for social media dimensions & first-party safe areas (Reels, TikTok, YouTube Shorts), encoder-safe aspect ratios, video bitrate math, SRT/VTT/ASS subtitle conversion, and BPM delay tables.

Six local CPU MCP tools for Markdown/HTML-to-PDF conversion, PDF text extraction, safe SVG-to-PNG rendering, and PDF link and chapter inspection. Linux/WSL2; no GPU, hosted inference API, or model download required.

An MCP server implementation that integrates with Minimax API to provide AI-powered image generation and text-to-speech functionality in editors like Windsurf and Cursor.

Gives LLM agents spatial awareness inside Autodesk Maya, enabling scene inspection and measurement, aesthetic and engineering audits, camera planning, checkpoint/rollback safety, asset import, and viewport or render previews. Agents can also execute arbitrary Python in Maya to build and verify 3D scenes against engineering rules instead of writing blind.

Official MCP server for Theta EdgeCloud's On-Demand Model APIs, providing access to 20+ AI models including image generation, audio transcription, and LLMs, directly from MCP-compatible clients.

Enables extraction of recipes from PDFs or JPG files and conversion into structured HTML, with interactive region selection and OCR via a web GUI.

MCP server providing image analysis tools for AI agents, including metadata extraction, favicon discovery, and placeholder generation.

Lets AI agents inspect local or remote videos by reading metadata, detecting shots and cuts, extracting frames as images, and checking keyframes for seeking and streaming, all via local FFmpeg without an API key.

Enables AI-driven 3D modeling and scene creation in Blender, allowing LLMs to create, modify, and manipulate objects, materials, and assets through natural language.

Enables AI assistants to work with local files — merging, compressing and editing PDFs, converting and resizing images, formatting text and data formats, running calculators, generating QR codes and barcodes, and producing invoices, resumes and other documents. Everything runs privately on the user's own machine with no uploads, accounts or API keys, and outputs can be chained from one tool to the next.

Enables MCP clients to discover OpenRouter image and video models, generate and edit images, create variations, launch and monitor video jobs, and save resulting media into authorized local project directories with cost controls.

Provider-neutral Vision MCP Server — image analysis via 10 inference providers through a single MCP server.

一个MCP视觉分析工具，将本地图片交给豆包视觉模型分析，帮助Claude Code和DeepSeek理解截图内容。

A comprehensive MCP server for Vue component development and Figma design restoration, featuring snapDOM-powered screenshots, pixel-perfect visual comparison, and automated SVG optimization.

Image Tools MCP is a Model Context Protocol (MCP) service that retrieves image dimensions and compresses images from URLs and local files using the TinyPNG API. It supports converting images to formats like webp, jpeg/jpg, and png, providing detailed information on width, height, type, and compressi

Enables MCP clients to use paid tools for secret scanning, agent-config auditing, and OG image rendering, with payments handled over the x402 protocol on Base.

Enables AI agents to perform deterministic video editing operations like trim, resize, add text, and more using MCP tools.

Enables AI coding agents to perform end-to-end medical image analysis locally, from inspecting CT/MRI/X-ray studies and running containerized segmentation models like MedSAM2, TotalSegmentator, and HD-BET to refining masks, measuring volumes, and writing reports. It pairs preset or custom guideline protocols with a code-customizable viewer that renders images back to agents as annotated PNGs and to humans as interactive HTML.

Enables AI agents to perform image processing tasks such as sprite sheet splitting, resizing, cropping, and batch operations on local images.

Enables AI agents to generate images, videos, and lip-sync media, and to query wallet balances via the Open Generative Studio instance.

Enables AI agents to perform file operations through the GigAI Tools API, such as merging PDFs, converting and compressing images, extracting PDF text, and generating QR codes, with results saved locally and tools synced from the live API catalog.

Exposes Open Video Guide functions to MCP clients, enabling conversion of tutorial videos into illustrated, verifiable guides with timestamps, evidence, and review states.

A server that integrates Blender with local AI models via the Model Context Protocol, allowing users to control Blender using natural language prompts for 3D modeling tasks.

A collection of miscellaneous tools for Claude, Cursor, and MCP-compatible clients. Includes OCR (Optical Character Recognition) capabilities leveraging the Google Gemini API.

Lets MCP clients drive a real iPhone from a Windows PC, exposing screenshots, accessibility-tree and OCR inspection, taps, typing, and swipes.

Free, no-auth tools for short-form video creators: Reels, TikTok and YouTube Shorts safe zones, caption placement checks, video bitrate and file-size math, SRT subtitle validation and platform export settings. TypeScript on Cloudflare Workers; hosted endpoint https://rast-creator-tools-mcp.studio-c25.workers.dev/v1/mcp. By Rast Creative Studio (rastcreative.com/en/tools/).

Enables users to run a 12-tool media pipeline with local FFmpeg and BYOK cloud providers for keyframe bridging, audio/TTS generation, inpainting/outpainting, background removal, 4K upscaling, contact-sheet slicing, and dual-lane timeline compilation to MP4/FCPXML.