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.
-
bailian-image-understanding-mcpupdated this year
阿里云百炼通义千问Qwen-VL图片内容理解MCP工具
npm MIT -
understand-image-mcpgithub.com/kakaxi3019/understand-image-mcpupdated this year
MCP server for image understanding using any OpenAI-compatible vision API
npm MIT -
@mcpcn/image-understandingupdated this year
Analyze and interpret images with the Zhipu AI GLM vision models
npm MIT -
智谱GLM-4V-Plus-0111 图片内容理解MCP工具
npm MIT -
An end-to-end AI-powered relevance and visual content-matching engine with MCP and RAG capabilities, designed to evaluate, rank, and pair imagery with textual context using multimodal embeddings and deep visual-semantic scoring
AGPL-3.0 ★ 1 -
MCP Server for Image/Video Understanding using Doubao Vision Model
npm MIT -
A small MCP server and Agent Skill for image/video understanding and image generation.
npm MIT -
tf-tools-mcpgithub.com/a2c-smcp/tf_tools_mcpupdated this year
Image generation and understanding tools using OpenRouter and Zhipu AI
pypi MIT -
通用图像 MCP 服务器:图像理解/OCR/对比/Gemini 生图,可插拔多模型 | Universal image MCP server: understanding, OCR, comparison & Gemini image generation with pluggable models
MIT ★ 1 -
MCP server for image/video understanding & generation (Gemini/OpenAI/Grok)
pypi Apache-2.0 -
@databytesolutionid/databyte-mcpupdated this year
DataByte AI MCP Server - provides web_search and understand_image tools
npm -
MCP server for Fanar API tools: Islamic RAG, image generation (with resizing), image understanding, thinking mode, and translation.
npm None -
claudeopus-mcpupdated this year
ClaudeOpus MCP server — web search and image understanding tools for AI coding agents
npm MIT -
opusmax-mcpupdated this year
OpusMax MCP server — web search and image understanding tools for AI coding agents
npm MIT -
opuslive-mcpupdated this year
OpusLive MCP server — web search and image understanding tools for AI coding agents
npm MIT -
opuscode-mcpupdated this year
OpusCode MCP server — web search and image understanding tools for AI coding agents
npm MIT -
minimax-unified-mcpgithub.com/exomind-team/minimax-unified-mcpupdated this year
Unified MiniMax MCP server for multimodal generation, Token Plan search, and image understanding.
MIT ★ 1 -
@xyzensun/visionmcpupdated this year
MCP stdio server for image understanding through configurable multimodal providers (OpenAI / Anthropic / Gemini formats).
npm MIT -
MCP server for Xiaomi MiMo multimodal understanding API (image, audio, video).
MIT -
prismrelay-mcpgithub.com/Arnoldkevin/prismrelay-mcpupdated this year
Vision-first local MCP that gives text-only Agents image understanding through Agnes AI (BYOK).
MIT ★ 1 -
visionpoweractive
VisionPower: a portable image understanding MCP server for Codex, Claude Desktop, Cursor, and other agents.
npm MIT -
nvidia-media-mcpgithub.com/DrCrypto911/nvidia-media-mcpupdated this year
MCP server exposing NVIDIA NIM media tools for image generation, OCR, and video understanding
★ 2 -
@imsus/pi-extension-minimax-coding-plan-mcpgithub.com/imsus/pi-extension-minimax-coding-plan-mcpupdated this year
MiniMax Coding Plan extension for pi coding agent - provides web_search and understand_image tools
npm MIT -
kv-agent-visiongithub.com/Kvxw1105/kv-agent-visionupdated this year
Give pure-text LLM agents eyes: zero-dependency image understanding, OCR & image Q&A via MCP server + standalone Python script. 给纯文本 AI Agent 的图片理解能力(看图/OCR/图片问答)。
MIT -
hyc-image-mcpupdated this year
MCP server for image understanding and OCR
pypi MIT -
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 -
vlm-mcpgithub.com/example/vlm-mcpupdated this year
VLM Image Understanding MCP Server - Support OpenAI protocol compatible VLMs
pypi MIT -
minimax-coding-plan-mcpgithub.com/seepine/minimax-coding-plan-mcpupdated this year
Mcp Server For MiniMax of web_search and understand_image
npm MIT -
agnes-image-mcpgithub.com/hskelp9527-pixel/agnes-image-mcpupdated this year
MCP server giving any AI client image generation and image understanding via the Agnes API. One key, free tier, works with text-only models like DeepSeek.
MIT -
image-vision-mcpgithub.com/staticdeng/image-vision-mcpupdated this year
Multi-model vision MCP server (GLM-4.6V, Kimi, Qwen-VL, GPT-4o) that lets text-only coding models in Claude Code see and understand images.
npm MIT -
@trinity-mcp/trinity-visionupdated this year
Trinity Vision — local MCP that gives non-vision models image understanding via Trinity API
npm MIT -
Turn images into structured information for AI agents. OCR, image understanding, colours, layout, CLI and MCP.
Apache-2.0 -
MCP server that gives text-only AI agents image understanding via vision APIs
npm MIT -
AI vision plugin — image analysis, OCR, and visual understanding via LLM providers — 6 MCP tools.
MIT -
vision-mcpgithub.com/weekitmo/vision-mcpupdated this year
MCP server for image understanding through OpenAI-compatible vision APIs. To provide image recognition capabilities for those large models that do not support Multimodal.
MIT -
Simple mcp server that let's understand pdf as image
npm ★ 5 -
dsh-luma-visiongithub.com/fuzzysoul/dsh-luma-visionupdated this year
Vision bridge for DeepSeek Harness (dsh): image understanding for text-only models via luma-mcp, free Qwen3-VL-Flash by default. 视觉理解插件:让纯文本模型获得看图能力(截图/报错/OCR/UI 分析)。
npm MIT -
image_tools_mcpgithub.com/ironsheep/image_tools_mcpupdated this year
A collection of tools to help an AI agent understand images through requests. After giving a single image, the request to zoom in and look about colors, measure dimensions, just a miscellaneous feature set to extend an AI agent in image handling.
go MIT ★ 8 -
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 -
Local MCP + REST server on your own NVIDIA GPU: Whisper large-v3 transcription + lightweight video understanding (keyframes as images + a timestamped transcript) — a simple, self-hosted take on Google Gemini–style video analysis. Rust (rmcp + whisper-rs/CUDA).
MIT -
Universal MCP vision tools (image + video frame understanding). Delegates to any OpenAI-compatible multimodal model, so text-only agents like DeepSeek can "see" via tool calls.
npm MIT -
visual-mcpgithub.com/aizcutei/visual-mcpupdated this year
An MCP server that gives LLMs without vision the ability to read and understand images.
-
TypeScript MCP server for image understanding, OCR and multimodal API integration
MIT -
vision-mcpgithub.com/forloopcodes/vision-mcpupdated this year
An MCP server that helps non-vision models extract and understand images and screenshots via OpenRouter multimodal models.
MIT ★ 3 -
vision-mcp-servergithub.com/Markusbetter/vision-mcp-serverupdated this year
为你的文字大模型加入一双眼睛。Vision MCP Server adds image understanding to MCP agents by calling a separately configured vision model.
npm MIT ★ 10 -
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 for Grok AI with chat, reasoning, live search, image understanding, and generation capabilities
★ 1 -
tonyq-mimo-mcp-serverupdated this year
MCP Server for MiMo multimodal capabilities (image, audio, video understanding, ASR, TTS)
npm MIT -
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 -
zhipu-glm-vision-mcpupdated this year
MCP server for GLM-4.6V-Flash multimodal understanding (image/video/file) via Zhipu API
pypi MIT -
deepseek-vision-mcpgithub.com/kgamv/deepseek-vision-mcpupdated this year
Local-first MCP server for image understanding with Ollama vision models.
MIT ★ 1 -
qwen-vision-mcpgithub.com/FUXIN-zhang/qwen-vision-mcpupdated this year
Qwen-VL vision MCP server - image understanding (describe + OCR) for Codex / Claude Code / Cursor via Alibaba DashScope
MIT -
server that shows trending tokens and integrates Grok, xAI image understanding and vision (interpreted as a vision-capable AI), and Claude's computer use capabilities.
★ 23 -
bioimage-mcp-servergithub.com/Ichoran/bioimage-mcp-serverupdated this year
bioimage-mcp-server gives your LLM agents high-level access to microscopy data by wrapping Bio-Formats and common image-understanding tasks in a MCP server
GPL-3.0 -
search-and-vision-mcpgithub.com/dimthink/search-and-vision-mcpupdated this year
Give any LLM eyes and a search engine. Universal MCP server: web search (Tavily/Exa) + image understanding (any OpenAI-compatible VLM).
MIT -
look-at-deepseekupdated this year
Lightweight multi-channel MCP server for vision understanding and OCR. Integrates multi-provider failover, transient retry, and clarity-first image compression. stdio + Streamable HTTP transports.
npm MIT -
This is a Model Context Protocol server that helps you work with PDF, DOCX, and Excel files in a more intelligent way. The server extracts text, understands document structure, pulls out metadata and embedded images, and even creates new documents with professional styling. It is designed to work with AI agents like LM Studio, Zed.
MIT ★ 1 -
magiclane-mcp-serverno update data
The Magic Lane Model Context Protocol (MCP) Server enables any AI agent or application to become a geospatially intelligent assistant, capable of acting as a reliable companion for pedestrians, cyclists, and drivers alike. Built on top of Magic Lane's advanced mapping and routing technology, this TypeScript-based MCP server empowers AI agents to: - Understand and process geospatial data - Interpret user intent in a spatial context - Deliver accurate, contextually relevant navigation guidance By leveraging Magic Lane's global map data and real-time geospatial intelligence, the MCP Server enables deeply personalized navigation and trip-planning experiences through core tools: - Intelligent Search: find addresses, points of interest (POIs), or coordinates with intelligent search capabilities and POI category filtering. - Smart Routing: generate optimized routes between multiple waypoints with support for various transport modes, route preferences, and dynamic POI integration. - Round Trip Planning: create circular routes that start and end at the same location, perfect for jogging routes, cycling loops, or delivery runs. - Reverse Geocoding: convert geographic coordinates into detailed address information including street name, city, state, country, and postal code. - Isochrone Analysis: calculate reachability polygons showing areas accessible within specific time or distance constraints. - Route Visualization: create visual map images of calculated routes, isochrones, and round trips for immediate geographical context and presentation. - Geofence Management: create, manage, and query geographic boundaries for asset monitoring, location-based alerts, and spatial analysis with support for polygons, circles, and rectangles. - Interactive Map: Display an interactive vector tile map directly inside the conversation using MapLibre GL JS and MagicLane vector tiles. Supports location views, route visualization, isochrone overlays, round trip routes, search result markers, geofence areas, and custom coordinate paths — with one or many overlays per map and pan/zoom interactions. The map functionalities can be visualized as high-quality map images through our new beta feature to generate custom map views with markers, bounding boxes, or location-centered areas without route calculation, complementing route visualization for routes, isochrones, and round trips. Together, these capabilities enable AI agents to act as true geospatial copilots - understanding spatial context, anticipating user needs, and optimizing every journey with precision and ease.
smithery -
visual-understand-mcpupdated this year
视觉理解 MCP Server - 为不支持视觉的编码模型提供图片理解能力
pypi -
@cqsjjb/mcp-vision-understandingupdated this year
MCP server for vision understanding - 支持图片上传和分析功能
npm MIT