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.
-
llm_visiongithub.com/1710782766/llm_visionupdated this year
Give vision to vision-less LLMs — a local MCP server powered by Alibaba DashScope
MIT -
@mseep/llm-vision-mcpupdated this year
An MCP server that gives vision capabilities to any LLM. It accepts images (file paths, URLs, or base64) and sends them to a vision-capable LLM, returning text descriptions that non-vision LLMs can use.
npm MIT -
llm-vision-mcpgithub.com/me9rez/llm-vision-mcpupdated this year
给文本模型装上眼睛:MCP Server 借助 OpenAI 兼容视觉模型(默认 ModelScope 免费通义千问VL)把图片文件转为文字描述,让 DeepSeek/GLM 等文本模型也能看图说话。本地 stdio 运行,Claude Code / Opencode 即插即用。
MIT ★ 4 -
her-eyesgithub.com/Penty-d/her-eyesupdated this year
带上她的眼睛 · Give a text-only LLM eyes — a single-binary MCP tool that lets agents like Claude Code / Codex call a vision model to extract structured key information from images.
MIT ★ 2 -
Give text-only LLM agents eyes: an MCP server + CLI that describes images through a vision-language model (VLM) API.
npm MIT -
vision-mcpupdated this year
MCP server for image analysis using Vision Language Models
pypi MIT -
Perceptron MCP server for high-accuracy visual perception powered by fast, efficient vision-language models
npm Apache-2.0 -
A sleek C# class library designed to integrate a local Model Context Protocol (MCP) server with a local Large Language Model (LLM), tailored for Godot-based games. This library empowers your LLM to seamlessly interact with the game world through structured tool commands, bringing your Echoes of Ir-style vision to life.
MIT ★ 1 -
MCP server for image analysis using the InternVL3 vision-language model
-
A repository showcasing integration of specialized computer vision tools with language models through MCP.
★ 1 -
Vision Test is an MCP (Model Context Protocol) server that provides a standardized way for AI agents and Large Language Models to interact with mobile devices.
MIT ★ 1 -
vision-mcpgithub.com/guorui999/vision-mcpupdated this year
MCP server for image analysis — give LLMs vision capabilities via external visual API
★ 2 -
Open-source MCP vision server that gives text-only LLMs and AI agents image understanding, OCR, visual analysis, UI inspection, and multimodal capabilities.
pypi MIT ★ 1 -
MCP server that adds vision capability to any LLM by routing image analysis to vision-capable OpenRouter models
npm MIT -
MCP Server that gives DeepSeek (and other text-only LLMs) vision capability via third-party OpenAI-compatible vision APIs
pypi MIT -
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 -
Vision sidecar MCP server — gives text-only LLMs the ability to see images. Supports OpenAI AND Anthropic API formats.
MIT -
mimo-vision-mcpgithub.com/SeverinQuan/mimo-vision-mcpupdated this year
Community MCP vision bridge for Xiaomi MiMo Vision, enabling image understanding for text-only LLM agents.
MIT ★ 7 -
@lutery/vision-mcpgithub.com/lutery/mcpupdated this year
MCP Server providing vision capabilities for LLMs via GLM-4.6V, SiliconFlow, ModelScope, OpenAI, Claude, Gemini, and Coding Plan (Kimi K2.5)
npm MIT -
MCP server providing OCR capabilities to LLMs via Google Cloud Vision API - Read scanned PDFs, handwritten text, and images with any orientation
pypi MIT ★ 1 -
Standalone MCP server for image recognition via LLM vision API — OCR, image analysis, structured extraction, screenshot-to-accessibility-tree
MIT ★ 1 -
vision-bridge-mcpgithub.com/mikhailsal/vision-bridge-mcpupdated this year
A lightweight Model Context Protocol (MCP) server for retrieving local and remote images for LLM vision models, featuring metadata extraction and configurable availability retries.
★ 1 -
mcp-local-visiongithub.com/jshsakura/mcp-local-visionupdated this year
Give text-only LLMs (GLM, DeepSeek, ...) eyes. MCP server that reads images and PDFs with a vision model on your own GPU — no API keys, nothing leaves the machine.
-
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 -
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 -
dsh-vision-mcpgithub.com/moton16/dsh-vision-mcpupdated this year
Give your text-only LLM eyes: an MCP server that reads images via external OpenAI-compatible vision models (OpenAI, Qwen-VL, GLM, Gemini, Grok, Ollama...) with automatic provider fallback on rate-limit/errors.
npm MIT -
mcp-vision-bridgegithub.com/KuaaMU/mcp-vision-bridgeupdated this year
MCP server that gives text-only LLM coding agents vision — analyze images via any multimodal model (mimo, Claude, Gemini, OpenAI-compatible). Works with Claude Code, Codex, Kimi, opencode, PI.
MIT ★ 13 -
mcp-vision-bridgeupdated this year
Give text-only LLM coding agents (DeepSeek V4 Flash/Pro, Qwen, Kimi) vision via any multimodal model. One analyze_image tool — paste or drag in one or many images, analyzed in a single call, scoped to the current session. Works with Claude Code, opencode,
npm MIT -
vision-primitives-mcpgithub.com/zouyuanqing/vision-primitives-mcpupdated this year
Vision-primitives MCP server for text-only LLMs: describe, locate (coordinates), OCR with bbox, annotate, crop, zoom, automated anomaly scanning, computer use — powered by Xiaomi MiMo V2.5. Single-file Python, Pillow-only dependency.
MIT ★ 9 -
One vision layer for AI agents on Windows - a single MCP server to see and act on desktop apps, Electron windows, and the browser (undetected). Screen as structured text, so text-only LLMs work too.
MIT -
AI vision plugin — image analysis, OCR, and visual understanding via LLM providers — 6 MCP tools.
MIT -
@keohanoi/vision-mcpupdated this year
MCP server that gives any text-only LLM vision — image analysis, OCR, comparison, region zoom, and video frame analysis.
npm MIT -
@zqt1125/clipboard-vision-mcpgithub.com/zqt1125/clipboard-vision-mcpupdated this year
Clipboard-first MCP server that gives vision-less LLMs image recognition via OpenAI-compatible vision models. Enhanced: primary+backup model failover, TTL result cache, Chinese description output.
npm MIT -
blind-vision-mcpgithub.com/alexjm19/blind-vision-mcpupdated this year
MCP server that gives vision to any text-only LLM — 100% local, no API bills. Gemma 4 E2B (LiteRT) for vision + SDXL-Turbo for image gen
pypi MIT ★ 1 -
claude-vision-mcpgithub.com/EDMOK/claude-vision-mcpupdated this year
MCP server empowering text-only LLMs with image analysis via any OpenAI-compatible vision API
MIT ★ 5 -
Universal MCP vision server for analyzing images with any LLM (OpenRouter, OpenAI, Anthropic, Google Gemini, Ollama)
npm MIT -
A simple MCP server that reads local images and returns them as ImageContent for LLM vision analysis
pypi MIT -
renderly-mcpgithub.com/xufei547/renderly-mcpupdated this year
MCP server for Renderly — clean web screenshots & content for AI agents (vision models, LLMs, RAG).
MIT -
AI claims triage for car damage: custom-trained vision models as tools for an auditable LLM agent. Models measure, the agent reasons, rules decide.
MIT ★ 3 -
Give an AI eyes for video — turn a clip into a numbered frame grid + transcript a vision LLM can read.
MIT -
MCP server that turns a FigJam board into queryable LLM context — read via the Figma API, clustered with geometry + vision. No PDF export.
npm MIT ★ 1 -
agent-vision-mcpgithub.com/kitlau86/agent-vision-mcpupdated this year
An MCP server that gives non-vision LLMs the ability to "see" images. Plug in any OpenAI-compatible vision API (Gemini, Qwen-VL, OpenAI, or self-hosted) and your text-only model — like DeepSeek in Claude Code — can analyze screenshots, OCR text, read charts, and more.
MIT ★ 10 -
A local MCP server that gives unimodal LLMs multimodal vision — image/video recognition with multi-turn iterative analysis.
npm Apache-2.0 -
vision mcp to connect non-image modality llm with vision supported llm
-
Give text-only LLMs eyes: a proxy swaps images/PDFs for stable text references, and an MCP ask_image tool lets the model question a separate vision model.
MIT -
winvision-mcpgithub.com/zaxbysauce/zaxbyuiaupdated this year
Windows 11 desktop automation and vision-LLM QA via MCP
pypi MIT -
Video frame extraction & composition service for AI vision pipelines, extracts frames via FFmpeg and composes them into 1×1/2×2/4×4 grid sheets for multimodal LLMs. REST API, Web UI, and MCP server over one core engine.
Apache-2.0 ★ 2 -
mcp-sightgithub.com/momo1037/mcp-sightupdated this year
MCP server that gives Claude Code sight — describe images using a vision-capable LLM
npm MIT -
Local-first AI-to-3D pipeline: LLM planning, validated Blender generation behind an MCP tool boundary, read-only vision review, semantic motion, and GLB/MP4 export with a FastAPI + Three.js studio.
GPL-3.0 ★ 9 -
luma-mcpgithub.com/JochenYang/luma-mcpupdated this year
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 coding models without native vision — analyze screenshots, errors, UI and documents via major vision LLM providers.
npm MIT ★ 116 -
mcp-recognize-imageupdated this year
MCP server that lets text-only models 'see' images via configurable vision LLM providers with priority fallback
pypi MIT -
macos-mcpgithub.com/BetterThanAny/macos-mcpupdated this year
MCP server exposing native macOS capabilities (Spotlight, Shortcuts, Calendar, Reminders, screencapture, Vision OCR, browser tabs, Mail) to LLM agents. Bun + TypeScript + Swift Vision, stdio-only.
MIT -
eyes-mcpgithub.com/JamesbbBriz/eyes-mcpupdated this year
👀 Give any text-only LLM eyes — local vision (VLM + OCR) for coding agents, via MCP. Zero API keys, nothing leaves your machine.
MIT -
my_tiny_agentgithub.com/yanjin101/my_tiny_agentupdated this year
Spec-driven small LLM agent that operates a real desktop end-to-end (OCR + YOLO + Win32), no vision LLM required. 规范驱动的端到端桌面操作 Agent。
MIT -
visual-mcpgithub.com/aizcutei/visual-mcpupdated this year
An MCP server that gives LLMs without vision the ability to read and understand images.
-
38 tools for Local LLMs — Google Search, live feeds, email, documents, QR codes, Wikipedia, S3 upload, vision, OCR, video transcription. No API key required.
pypi MIT -
Screenshot capture and annotation tool with LLM vision analysis, OCR, and MCP server for AI agent integration
EPL-2.0 -
image-tiler-mcp-servergithub.com/keiver/image-tiler-mcp-serverupdated this year
MCP server that prevents LLM vision downscaling, tiles large images & screenshots so Claude, GPT-4o, and Gemini see every detail
npm MIT ★ 3 -
Desktop vision and control for LLMs over MCP — for Linux and Wayland, where Claude's built-in computer use isn't available. Absolute-uinput input, pixel-exact on COSMIC.
MIT ★ 1 -
PokéDex con IA: agente con tool calling escrito a mano, servidor MCP, 3 LLMs con fallback (Groq → Gemini → Anthropic), evals y visión. Next.js + Supabase (RLS) + FastAPI.
MIT