Screenshot MCP Servers

MCP server for browser and desktop automation: OCR, image recognition, real mouse and keyboard input

Give Claude the ability to watch and understand videos — Claude Code plugin with frame extraction and multimodal audio analysis

Use Hugging Face Spaces for open-source image generation, chat, vision and more, with image, audio and text uploads and downloads.

Computer vision-based image recognition and editing tools.

Programmatic control over Windows system operations including mouse, keyboard, window management, and screen capture using nut.js.

Transform YouTube videos into a compounding knowledge base with transcripts, vision analysis, and agentic search. Works as an MCP server…

VisionCraft MCP delivers up-to-date, specialized computer vision and Gen-AI knowledge directly to Claude and other AI assistants.

多模型视觉理解 MCP 服务器，为不支持图片理解的 AI 编码模型提供视觉能力：分析截图、报错、UI 与文档，可接入多家主流视觉大模型。Multi-model vision MCP server that adds image understanding to AI…

Advanced computer vision and object detection MCP server powered by Dino-X, enabling AI agents to analyze images, detect objects, identify…

Capture website screenshots, tiling full pages into 1072x1072 chunks for Claude Vision, with configurable viewports and wait strategies…

Specialized MiniMax Model Context Protocol (MCP) server designed for coding-plan users, featuring AI-powered search and vision analysis…

Image, video and object-detection analysis with Google Gemini and Vertex AI for UI/UX evaluation, visual regression testing and interface…

Computer vision models as MCP servers

Zero-token, on-device vision for AI agents — OCR, pixel-exact UI targeting, and face grouping on Apple Vision. Pure Swift, single binary,…

TVControl by Ferrox Labs — TradingView MCP System. AI remote control for TradingView Desktop. 88 MCP tools driving symbols, indicators,…

Access xAI's Grok API with agentic tool calling, image generation, vision and file support.

Computer use for Hyprland: semantic desktop state over IPC, plus vision and native input

A token-efficient, provider-agnostic vision layer for reasoning models via MCP.

It can run on the phone itself, or on any other machine that can reach the phone through `adb`. With a vision-capable model, it can…

The Trend Vision One Model Context Protocol (MCP) Server enables natural language interaction between your favourite AI tooling and the…

An MCP server that provides image recognition 👀 capabilities using Anthropic and OpenAI vision APIs

Agent Library personal knowledge base with a search and retrieval system MCP Server and CLI. Preconfigured local models and support for…

Gemini Vision & Image Generation MCP for Claude Desktop and Claude Code

Terminal for AI coding agents: persistent PTY sessions, incremental reads, headless screen capture, multi-agent orchestration and a web…

Control FiftyOne computer vision datasets through AI assistants using 80+ operators.

MCP server — control remote desktops via VNC with a native Swift daemon and Apple Vision OCR

Developer tools for file editing, shell command execution and screen capture.

Excel MCP with image extraction and write support — AI agents see and edit xlsx files

DeepSeek web vision model as an MCP server with browser auto-login.

Browser automation MCP server with 84 tools. Pure CDP, DOM diffing, vision hybrid.

3D vision and medical imaging: 43 datasets with licences, 73 algorithms on clouds, meshes, CT/MRI

Local OCR & screen understanding for agents: read any window, find what to click. No uploads.

Mobile E2E MCP (51 tools): iOS + Android, native UI + canvas/WebGL, no-vision, RN debug

Hybrid computer-use runtime combining the accessibility tree, Chrome DevTools Protocol and vision into structured context, with offline…

AI control of Android/iOS devices. Screenshots, UI tree, AI vision, Flutter, video. 49 tools.

Replicate MCP server - image, video, audio, speech, LLM, vision, upscale, 3D, training. 36 tools.

Tile large images and web page captures (via Chrome CDP) so vision models see full resolution, with model-specific token estimates and…

MCP RAG: index PDFs, repos, YouTube, Discord, text; optional YouTube vision; query with citations.

Pay-per-request AI access via Bitcoin Lightning through LightningProx, with vision and multimodal support.

Extract handwritten math formulas from uploaded images as LaTeX using a vision-language model, with a Vue frontend.

Read markdown with inlined images and index headings for agentic RAG workflows.

Screen OCR on macOS via FreezeText: freeze the screen and extract text with Apple Vision, OCR regions or images, and search capture history.

Full-text PDF search with Apple Vision OCR via the PDF Content Search app, with date, category, sender and amount filters, wildcards and…

Lightning-paid (L402) Bitcoin mempool data (fees, whale alerts, fee prediction, tx status) plus self-hosted AI inference for text, code,…

51 Baidu AI MCP tools: OCR, Vision, LLM, Speech, NLP. Pay-per-call from $0.001.

Tactile browser control and multimodal visual vision MCP bridge for Google Chrome.

Catch bad animations before they ship. Deterministic motion audit + vision-LLM design review.

Color-vision accessibility: check palettes and images for colorblind safety, generate safe palettes, simulate color blindness and create…