"Super User" matching MCP servers:

Enables AI agents to analyze images via user-configured cloud vision APIs (Gemini or OpenAI-compatible), returning structured results such as summaries, OCR text, and objects.

Enables visually lossless batch compression of JPEG, PNG, WebP, AVIF, GIF, and SVG files, writing results to a temporary preview directory with size, encoder, and quality-score details. Originals are only replaced atomically after the user confirms, with configurable effort levels and optional backups.

Enables AI agents to generate game-ready 3D assets from reference images with PBR textures, and to retexture meshes the user already owns, while recording full provenance for every generated file.

Creates narrated 9:16 documentary videos from user-described topics using Wikimedia images and AI voiceover, rendered entirely on your machine.

Enables local creation of 9:16 videos from user-authorized images, with background music, OCR keyword highlighting, and annotation animations through MCP tools.

Enables an AI assistant to convert images among HEIC, JPEG, PNG, WebP, and AVIF entirely on the local machine, including converting a folder of files into a single zip. Access is confined to a user-specified root directory, metadata is stripped by default, existing files are never overwritten, and no network requests or telemetry are used.

A self-hosted MCP server that enables AI agents to see and control a Windows PC through screenshots, built-in Arabic/English OCR, mouse, keyboard, clipboard, and application launching, with code-enforced consent and audit logging.

Enables agents to read and write CapCut desktop draft folders on local disk, assembling vertical 1080×1920 shorts with clips, titles, subtitles, music, transitions, and effects as drafts the user then opens and exports in CapCut. All writes are dry runs until explicitly disabled, and existing drafts are backed up before overwriting.

Provides five fail-closed MCP tools for validating reference images and sculpting plans, enabling user-owned procedural Three.js source creation through validated gates and grimoire lookups.

Enables AI agents to generate static QR codes as PNG images or SVG markup for any URL or text, entirely locally with no account or API key, and to obtain prefillable links to a free online QR designer. It also provides instructions for creating dynamic, tracked short-link codes.

Enables AI tools to capture and process screenshots of a user's screen, allowing AI assistants to see and analyze what the user is looking at through a simple MCP interface.

Enables MCP-capable AI tools such as Claude Code and Codex to operate the locally running XuanShang infinite canvas under one unified ruleset: creating projects and certification groups, uploading and certifying images and reference videos, placing assets on the canvas, building Seedance video nodes, submitting generation, and converting drafts to final videos. Credit-spending actions always require explicit user confirmation, and the plugin never reads or stores API keys.

Enables Claude Code, Cursor, Codex and other MCP clients to generate and edit images and videos directly in a project using AI subscriptions the user already pays for, without API keys or extra billing. Also provides local media tools such as background removal, video editing for social formats, and automatic resizing and optimization of results.

Enables AI clients to generate Perchance images and manage user keys via a lightweight MCP server that fits in 512MB RAM by offloading browser-based Turnstile solving to an external solver service.

Enables native Windows desktop automation through MCP by capturing screens with Set-of-Marks grounding, dispatching clicks, typing, hotkeys, and scrolling, managing windows and background sessions, and verifying actions with a visual safety oracle and Merkle audit trail.

An MCP server that visually reviews UI edit requests by comparing screenshots before and after edits, ensuring changes satisfy user requests.

Enables managing RunningHub workflows locally through Codex, including searching public models and prices, creating and validating workflow JSON, tracking projects, scenes, assets, and revisions in SQLite, and submitting single paid generation jobs with status polling, result download, and FFmpeg-generated previews. Requires explicit user confirmation before any paid run and prevents hidden automatic retries of uncertain submissions.

Provides comprehensive functionality including weather data, system utilities, Azure cloud management, and AI-powered image generation and editing. Features interactive parameter selection through MCP elicitation for enhanced user experience.

Connects an MCP assistant to the PicPrep desktop app, letting it open and inspect photo projects, view slides and tabs, ask the user questions, and propose changes that the user alone keeps or rejects. It runs locally over 127.0.0.1 and starts the app on demand, so nothing leaves the computer.

Enables LLMs to analyze images, videos, audio, and text files for AI-generated content using the Reality Defender API, with support for user file uploads and direct URL analysis.