- Conduid
- Marketplace
- #vision
MCP servers tagged vision
97 live MCP servers tagged "vision", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with vision.
Librechat
Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, A…
mediar-ai/screenpipe
run agents that work for you in the background based on what you do
SimpleMem
[ICML'26] SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal
jcdickinson/simplemem
A very simple semantic MCP memory store
mediar-ai/screenpipe
aware AI agents through a NextJS plugin ecosystem.
Oscribe
If you can see it, Oscribe can click it.
Pyvisionai
The PyVisionAI Official Repo
Deepseek Eyes
Windows-first local vision bridge: give text-only DeepSeek coding agents real eyes via the Xiaomi MiMo Token Plan (mimo-v2.5). MCP server + OpenCode plugin + VS Code Copilot exten…
Achatbot
An open source chat bot architecture for voice/vision (and multimodal) assistants, local(CPU/GPU bound) and remote(I/O bound) to run.
FlowVision
FlowVision，一键分析项目代码 · 自动生成架构流程图 · 可视化编辑 · MCP 实时同步
Vision MCP Server
Reliable vision MCP server with ordered fallback across ModelScope, Zhipu, and OpenAI-compatible models
Vision MCP Server
Reliable vision MCP server with ordered fallback across ModelScope, Zhipu, and OpenAI-compatible models
Opencode Minimax Easy Vision
OpenCode plugin that restores the paste-and-ask workflow for text-only models by saving pasted images and injecting MCP tool instructions
Chat
Chat Client for Your Service's MCP Server
Dsv Bridge Skill
🖼️ 给不会看图的大模型一双眼睛: 本地AI无法OCR/识别的图片 → DeepSeek识图模式(套壳 deepseek-vision-cli) 的 skill
image-tiler-server
MCP server that splits large images into optimally-sized tiles for LLM vision (Claude, OpenAI, Gemini, Gemini 3)
Opencode Easy Vision
Restore the “paste and ask” vision workflow for text-only models in OpenCode ⚡
EagleRAG
Search knowledge by what documents mean and how they look — not one or the other.
Vision Server
MCP server that exposes image analysis tools to LLMs via the Model Context Protocol.
Screenshot X402 CLI
CLI for screenshot-x402: MCP Streamable HTTP client with x402 USDC payments — health, screenshots, and vision analysis.
Pi Zai
Unofficial pi package that exposes Z.ai MCP server tools for web search, URL reading, repository reading, and vision workflows.
Doubao Vision MCP Server
MCP server for Doubao vision models via Volcengine Ark API
LLM Vision
A TypeScript MCP server that gives text-only LLMs image understanding through StepFun vision models.
Image Vision
MCP server for image recognition via vision models (extensible to multiple providers), with an HTTP image-intercepting proxy that lets text-only LLMs accept image input in Claude…
Vision Foundation
Vision understanding MCP service powered by local SmolVLM / SmolVLM2 / MiniCPM-V via llama.cpp
Openai Vision MCP Server
MCP server for secure, bounded OpenAI-compatible vision analysis
Vision Helper MCP Server
MCP server that adds vision capability to any LLM by routing image analysis to vision-capable OpenRouter models
Pi Vision Struct
⛔ 已停止维护（EOL 2026-09-13，仓库只读）· Deprecated & archived：给纯文本模型的数理化视觉通道 + GUI 控制；已被 DeepSeek-V4.1 原生多模态取代。Numeric-grade vision channel + GUI control for text-only models — superseded b…
Picture Identification MCP
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。
Phone Eye
MCP server that lets an AI agent see and operate an Android device you own over adb, for app testing and automation. Vision plus UI-tree fusion, for any MCP client.
Cc Vision Bridge
Vision bridge for Claude Code + text-only models (DeepSeek etc.): hooks, permanent cache, Action Guide.
Effero
Effero is a modular runtime for building agentic AI systems.
Dsh Vision
给 DeepSeek Harness（dsh 插件）与 Claude Code（MCP）提供视觉能力：本地 OCR（macOS / Windows）+ 云端 VLM（多供应商，OpenAI 兼容）
Media2md
Turn images into structured, searchable markdown with AI vision
Codex Vision Bridge
为纯文本 Codex 模型补上看图能力的 MCP 工具：支持 describe（看图描述/OCR）、locate（界面元素定位）、photo（图片内容保真）、ui（界面读屏）四种模式。一条命令安装。
Opencode Plugin View Image
OpenCode vision plugin to add view_image tool
Ollamabot
Local-first autonomous agent powered explicitly by local models via Ollama. It implements dynamic capability routing to dispatch specialized tasks (such as text chat, vision, audi…
bridgenode-ai/bridgenode-mcp
y @bridgenode/mcp` or remote `https://bridgenode.cc/mcp`.
DSH Plugins 4U
DSH 自建插件集合：微信桥接器 + GUI 微信入口补丁，一键安装
Bridgenode SDK Ts
BridgeNode — x402 pay-per-request AI inference. TypeScript SDK.
Zen Vision
给纯文本模型（DeepSeek 等）装上眼睛：用 OpenCode Zen 免费多模态模型（mimo-v2.5-free）把图片转成文字描述。单文件、零成本、多源自动切换 + 实时视力监控。
Sight MCP
让只会读文字的 Agent 拥有视觉能力
Web Agent
Local-first web & desktop automation toolkit: browser automation, video transcription, local OCR & VLM vision, desktop control — 数据全部本地处理，零上传
Hands
给她一双手：把手机 App 里的人设接上电脑的 335 个 MCP 工具（能看图、能读屏幕）· One exe, 335 MCP tools for your phone-side persona (Windows, MIT)
Blind Vision MCP
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
Vision Server
MCP server that exposes image analysis tools to LLMs via the Model Context Protocol.
Vision MCP
Let any AI agent see — analyze and describe images through the three.ws vision pipeline. Free NVIDIA NIM VLMs first, with an automatic server-side paid backstop. Pass an image URL…
Deepseek Vision MCP
通用视觉 MCP 服务器：为 DeepSeek 等无视觉模型补齐图片识别/OCR，支持智谱/OpenAI/通义千问/Kimi 等 OpenAI 兼容厂家
Agentic Vision
Persistent visual memory for AI agents — capture screenshots, embed with CLIP ViT-B/32, compare, recall. MCP server + Rust core library.
404
TEAM 404 : Project For Prabal (Hackathon) FarmGenius is an advanced, multi-agent agricultural assistant designed for Indian farmers, agri-entrepreneurs, and researchers. It combin…