- Conduid
- Marketplace
- #vision-language-model
MCP servers tagged vision-language-model
23 live MCP servers tagged "vision-language-model", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with vision-language-model.
OGAM
The Swiss Army Knife of Offline AI. Chat, see, speak, and generate images on your phone or Mac — GGUF LLMs, vision, Whisper speech-to-text, Stable Diffusion, tool calling, and loc…
AutoContents
扫描版 PDF 的书签自动生成工具，可以根据 PDF 目录页内容，为 PDF 设置可跳转的书签。
Images
MCP 图片分析服务器 — 在 AI 工具中直接分析本地图片、剪贴板截图或 Base64 图片数据
Jy Crpg Bench
A long-horizon CRPG benchmark for frontier agents. Raw 320x200 frames, Traditional Chinese, isometric navigation, twelve books to find.
Visbridge
Token-efficient vision capability layer for MCP clients (describe / OCR / inspect)
Vlm MCP Server
MCP Server for VLM - A Model Context Protocol server providing vision/video analysis, configurable with any model provider (Chat Completions / Responses / Anthropic).
Uitars MCP
Desktop + browser GUI agent MCP server. VLM-powered automation: screenshot → vision model → mouse/keyboard/Playwright actions. 9 MCP tools. Fits RTX 4090.
SkyVision.cpp
Multi-backend GGUF vision-language inference engine (moondream3.1 · VideoChat3 · Qwen2.5-VL · MOSS-VL · VideoMAE/ViViT · SmolVLM) with a unified CLI, Web UI and an MCP server for…
Deepseek Vision MCP
Secure MCP v2 server for DeepSeek V4 Flash Vision — analyze, describe, OCR, compare, locate, upload, and manage images from any MCP-compatible agent.
Deepseek Vision MCP
Local-first MCP server for image understanding with Ollama vision models.
Blink Skill
Enable AI to monitor your screen and provide proactive assistance based on your current activity using Claude Vision.
Shadow Vision
Open-source MCP vision server that gives text-only LLMs and AI agents image understanding, OCR, visual analysis, UI inspection, and multimodal capabilities.
Her Eyes
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.
Nvidia MCP
MCP server that gives Claude, Cursor and any AI agent free access to 100+ NVIDIA-hosted models (Nemotron, Llama, GPT-OSS, DeepSeek, vision, embeddings) with automatic task routing…
Claude Holo Unreal
Unreal Engine copilot for Claude Code — CLI + MCP server + skills + Python library. Drives the running UE editor via PythonScriptPlugin, falls back to H Company Holo3 vision groun…
Screen Use
browser-use, but for the entire desktop — give any AI Agent eyes and hands on Windows. MCP + SDK, VLM-optional, with visual loop, introspection and meta-learning.
Doc7
Convert any document—PDFs, Office files, scans, charts—into AI-ready Markdown for seamless search, quoting, and reasoning.
Adatile MCP
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…
Oai Chat
Multi-modal Chatbot based on OpenAI
Agent Eyes
Real vision for any AI agent. Screenshots it can actually look at, the design system read out of the live CSSOM, and every downloaded file checked before it is handed over — on an…
AI Scraping Stack
AI Scraping Stack — web intelligence platform for competitor analysis & automated scraping. Multi-agent pipeline extracts insights from URLs, analyzes screenshots with VLMs, gener…
Manga Vision MCP
Local stdio MCP server exposing OpenAI-compatible vision VLMs (primary/nsfw/fallback slots) for image conformance review
Deepseek V4 Qwen Mm
DeepSeek V4 Flash thinks. Qwen-MM sees. Measured stdio MCP vision composition.