MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Vision Studio - Touchless Computer Vision, Gesture Recognition, 3D Kinematics & MCP Server (design influenced by Material 3)
MIT -
MCP server and MLOps CLI to export, quantize, audit, benchmark and auto-tune PyTorch and ONNX computer-vision models for edge deployment.
MIT -
artsleuthgithub.com/ladyfaye1998/artsleuthupdated this year
Computational Art Analysis Framework — Brushstroke analysis, style attribution, anomaly screening, and interpretable visual explanations powered by vision transformers.
pypi MIT -
pixlintgithub.com/amitsingh-24/pixlintupdated this year
MCP server for managing, analyzing, and optimizing computer vision datasets
pypi PolyForm Strict License 1.0.0 -
PixLintgithub.com/amitsingh-24/PixLintupdated this year
Lint, curate, and prepare computer-vision datasets from your AI assistant MCP server.
NOASSERTION -
3D computer vision and medical imaging in Python: 43 public 3D and medical datasets loaded in one line with manifests and licences, 73 algorithms on point clouds, meshes and CT/MRI volumes (registration, segmentation, reconstruction), one typed object over Open3D, PyVista and SimpleITK, and an MCP server for AI agents.
pypi Apache-2.0 -
Free private photo-to-cartoon and print studio: local computer vision, image analysis, reusable recipes, optional text-model direction and local MCP tools.
MIT ★ 1 -
argusgithub.com/korisame/argusupdated this year
Vision-grounded macOS automation as a Claude Code MCP plugin (40 tools). Hybrid AX + Apple Vision OCR + CDP + Moondream cascade. Replaces Computer Use on macOS.
Apache-2.0 -
Claude-style computer use for any vision model in Cursor on macOS (MCP server: screenshots + accessibility tree + OCR)
★ 1 -
Windows computer-use MCP server for OpenCode, Claude Desktop and Codex CLI. Indexed UI-Automation controls, set-based tree filtering, verified clicks - no vision model, no pixel guessing.
Apache-2.0 -
⚡ Ultra-fast hybrid Browser & Desktop Computer-Use MCP Server (DOM + Native OS Accessibility + LiquidAI D1 Vision) with human-like physical mouse movement and Paint/canvas drawing.
MIT ★ 1 -
Computer use for Hyprland: semantic desktop state over IPC plus vision and native Wayland input, in one MCP server
pypi MIT -
Fast computer use for AI agents: event-driven settling MCP server - replaces time.sleep between clicks, waits for the UI to react and stop changing, returns the settled screenshot. No blind waits, no wasted vision turns.
NOASSERTION -
WinCU / Windows Computer Use / Computer Action / Windows MCP: an MCP server that lets AI models operate a Windows PC with screenshots, mouse, keyboard, clipboard, window control and UI Automation. Works with Claude, ChatGPT and other vision models.
MIT ★ 3 -
Advanced MCP server for intelligent computer use automation and AI agent operator control. Supports mouse and keyboard input, window-relative vision and coordinates, Retina display, and screenshot-based debugging. Designed for AI-driven workflows, app and
npm MIT -
👓 Computer vision–based automation tool for remotely controlling Android devices via Go server and custom client.
Apache-2.0 ★ 2 -
A MCP server that bridges AI agents to the Windows desktop. UI Automation, synthetic mouse/keyboard input, screenshots, window and application control, PowerShell, the registry, processes, the filesystem, and web scraping. No computer-vision model is required: the agent perceives the UI through the Windows accessibility tree.
MIT ★ 17 -
lucida-vision-mcpgithub.com/dongyushenqi/lucida-vision-mcpupdated this year
通用视觉感知 MCP 服务器（眼睛不是大脑）/ General-purpose visual perception MCP server (eyes, not brain)
MIT ★ 1 -
本地优先的多模态视觉 MCP —— 为无视觉 LLM（DeepSeek、GLM 等）提供可自定义端点的看图 / OCR / 文档解析能力。
MIT -
AxiomVision — Deterministic OS-Level Vision, Sub-Pixel OCR & Accessibility Automation Engine for AI Agents.
MIT ★ 1 -
pinterest-vision-mcpgithub.com/Kreminskaya/pinterest-vision-mcpupdated this year
Visual intelligence pipeline for AI agents — search Pinterest, analyze with LLM vision, store and retrieve by semantic similarity
★ 4 -
Point cloud ICP alignment, Recast navmesh baking, and camera extrinsics calibration for physical AI agents.
MIT -
chart-vision-mcpgithub.com/nessos666/chart-vision-mcpupdated this year
Local TradingView chart analysis via OpenCV + Tesseract OCR. No API keys, no GPU, runs fully offline — MCP server with color/level/zone detection.
MIT ★ 3 -
Open-source MCP vision server that gives text-only LLMs and AI agents image understanding, OCR, visual analysis, UI inspection, and multimodal capabilities.
MIT ★ 1 -
MCP vision server for AI agents, Claude, Cursor, OpenCode, VS Code, local LLMs, Ollama, LM Studio, OpenRouter, Gemini, image analysis, and video understanding.
GPL-3.0 ★ 17 -
Enable AI to interact with Windows apps by viewing screens, reading UI, clicking, typing, and automating tasks with OCR and window detection.
MIT ★ 5 -
Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.
npm NOASSERTION ★ 42 -
A high-performance desktop app interaction framework for AI agents — faster, cheaper, more accurate. / 让 Agent 操作桌面软件更快、更准、更省。
NOASSERTION ★ 8 -
korgi-vision-ossgithub.com/c0de4un/korgi-vision-ossupdated this year
Open-source, self-hosted platform for distributed image analysis using local Vision LLMs (Moondream 2 / Qwen 2.5). Built with Rust, Axum, and Vue 3.
MIT ★ 1 -
FastMCP server for Moondream vision language model
pypi MIT -
本地视觉理解 MCP 服务，为 AI agent 提供识图能力：通过 vision / ocr / list_models / providers 四个 MCP 工具描述截图、界面、图表与照片。
MIT ★ 5 -
Local-first MCP server for BeamNG.drive, BeamNGpy, Lua extensions, and GPU vision
MIT ★ 2 -
Let AI models use your Windows computer through MCP: screenshots, mouse, keyboard, windows, UI Automation and OCR, with every monitor and every window's position made explicit to the model.
NOASSERTION -
Camera vision MCP server: multi-camera, gesture recognition, object detection, scene understanding. Give your AI agent eyes
MIT ★ 1 -
Ui.Vision MCP: MCP server for browser and desktop automation (RPA) with OCR, image recognition and real mouse/keyboard input. Works with Claude Code, Claude Desktop, Codex, Cursor, Windsurf, VS Code, LM Studio and any other MCP client.
npm MIT -
—
MIT -
MCP server that lets AI agents analyze, describe and read text in images through the free-first three.ws vision API.
NOASSERTION ★ 10 -
Tuba-Workflow-MCP-Servergithub.com/DevisionX/Tuba-Workflow-MCP-Serverupdated this year
Model Context Protocol server for Tuba Workflow
MIT ★ 2 -
albumentationsx-mcpgithub.com/dkosarevsky/albu-mcpupdated this year
Model Context Protocol server for AlbumentationsX augmentation previews, validation, and segmentation review.
pypi AGPL-3.0-or-later -
ArtSleuthgithub.com/ladyFaye1998/ArtSleuthupdated this year
AI Art Forensics & Analysis Framework — Brushstroke analysis, style attribution, forgery detection, and interpretable visual explanations powered by vision transformers.
MIT ★ 3 -
mcp-videogithub.com/ipythonist/mcp-videoupdated this year
MCP server for video intelligence — analyze any video with AI vision. Extract keyframes, transcripts, and trading strategies from YouTube, Instagram & 1000+ sites.
MIT ★ 4 -
MAVLink MCP server: let Claude, Codex or any AI agent fly ArduPilot drones over MAVLink. Missions, camera vision, SITL, safety-gated. pip install mavlink-mcp
MIT ★ 6 -
3D vision and medical imaging in one Python package: 73 algorithms, 43 datasets in one line, Open3D / SimpleITK / PyVista, MCP server for AI agents
Apache-2.0 ★ 10 -
Desktop + browser GUI agent MCP server. VLM-powered automation: screenshot → vision model → mouse/keyboard/Playwright actions. 9 MCP tools. Fits RTX 4090.
Apache-2.0 ★ 2 -
imagesorcery-mcpgithub.com/sunriseapps/imagesorcery-mcpupdated this year
An MCP server providing tools for image processing operations
MIT ★ 339 -
webcam_mcpgithub.com/pavel-kirienko/webcam_mcpupdated this year
An MCP server to give LLM agents access to a camera for taking photos
MIT ★ 6 -
Desktop automation MCP server — computer use for any AI agent: control screen, windows, mouse/keyboard, and Chrome via Model Context Protocol (stdio). Not a DSH plugin — DSH users install dsh-nuphus-mcp.
MIT ★ 334 -
albu-mcpgithub.com/dKosarevsky/albu-mcpupdated this year
MCP server for AlbumentationsX image augmentation workflows
AGPL-3.0 ★ 6 -
MCP-compliant image augmentation server using Albumentations
pypi MIT License -
An MCP-compatible image augmentation tool powered by Albumentations. Built for Claude, Kiro, and other AI agents.
MIT ★ 1 -
A multi-interface (REST and MCP) server for automatic license plate recognition
pypi MIT -
AdaTile-MCP: high-resolution image adaptive tiling MCP server for DeepSeek vision model (deepseek-v4-flash-vision-exp). L1-L6 pipeline (fastpath, saliency, adaptive tiling, Files API assembly, streaming VLM, rule-based merge) + eval harness. Setup: clone, run setup.bat, add your agent MCP config -> see README.
MIT -
PyMCPAutoGUIgithub.com/ahaufox/PyMCPAutoGUIupdated this year
🚀 赋予 AI Agent (如 Cursor, Claude) 视觉与操作能力的跨平台 MCP 服务端。让大模型像人类一样看屏幕、控键鼠、管窗口！(A GUI manipulation MCP server for AI Agents)
MIT -
Physical camera perception, measurement, and verification tool for MCP AI agents
pypi MIT -
Vision pipelines on a Hailo-8L M.2 NPU: MCP server (SCrFD face detect ~311 FPS, PaddleOCR v5, TinyCLIP embeddings), Spanish-aware OCR correction, measured multi-phase OCR quality program, and the Linux kernel VDMA stability patch. 100% on-device inference.
MIT -
A multi-interface (REST and MCP) server for automatic license plate recognition 🚗
MIT ★ 26 -
Point it at an image, an AI says what it sees. Florence-2 describer — MCP server + CLI (local, MIT)
MIT -
MCP server for Microsoft OmniParser: turn screenshots into structured UI elements for GUI agents (such as Claude Desktop / Cursor / Cline)
CC-BY-4.0 -
Physical camera perception, measurement, and verification tool for MCP AI agents
MIT -
UI structure extractor for text-only LLMs - pure Go binary, offline, CGO_ENABLED=0, MCP-native
npm MIT