- Conduid
- Marketplace
- #multimodal
MCP servers tagged multimodal
125 live MCP servers tagged "multimodal", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with multimodal.
Openai Vision MCP Server
MCP server for secure, bounded OpenAI-compatible vision analysis
Wechat AI Assistant
可执行任务的微信/桌面 AI 智能体：LangGraph · MCP · RAG · Tauri
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。
Seedance 2 AI
🎥 Generate AI-driven videos with Seedance 2.0, offering precise physics, lip-sync, and prompt accuracy for seamless content creation.
Synorive
Search your files by meaning and fact-check the web, fully offline.
Local Multimodal Infra
Local multimodal inference service
Garden Flow
Local-first AI workspace that turns research into content — collect, organize, ideate, write, generate media and automate.
Effero
Effero is a modular runtime for building agentic AI systems.
VideoXAgent
Online Video Agent Harness for Long Video Understanding.
Opencode Plugin View Image
OpenCode vision plugin to add view_image tool
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。
Flawless Take
Autonomous on-set AI continuity supervisor for film & TV. Multimodal vision diffing, scene memory tracking, 8 ADK tools, and FastMCP SSE streaming powered by Google Gemini & Googl…
Strathmore School AI App Builders Program Nov Dec Holidays 2026
November/December 2026 Holiday Program for www.strathmore.ac.ke students. A course on building AI apps for typical AI paradigms (e.g. Multimodal, RAG, tool use, AI agents, Text-to…
Mempalace Extended
Extension of the original MemPalace with document ingestion, image assets, MCP tooling, and folder watch.
Psibot
Always-on AI agent for Telegram, powered by Claude Agent SDK. Runs 24/7 on your Mac with your Max subscription. $0 API costs. Multimodal: voice, images, YouTube, browser automatio…
Visual Hear Understanding
alternative multimodal on non support multimodal
Minimax Unified MCP
Unified MiniMax MCP server for multimodal generation, Token Plan search, and image understanding.
Multimodal Desktop Agent
Modular desktop AI agent core with local/OpenAI-compatible LLMs, memory fallbacks, MCP-style tools and multimodal adapters.
Runninghub Connector
一个连接器顶掉一堆账号：350+ 模型覆盖图像/视频/音频/3D + ComfyUI 工作流 + AI 应用 + LLM，一句话从出图切到出片再切到配音，素材风格与余额都不分散。适合内容创作者/一人公司/小团队。开发者 AI芳程式，反馈 zzdh518
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
Gemini MCP Server
MCP server with 23 tools for Google Gemini API — chat, multimodal analysis, deep research, YouTube, Files API, embeddings, and more
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
Deepseek Vision MCP
Local-first MCP server for image understanding with Ollama vision models.
Glint
On-device multimodal search for macOS: photos, video moments, audio, PDFs and docs, by meaning. MLX + EmbeddingGemma 2, with an MCP server for agents.
Pensyve
Universal memory runtime for AI agents. 8-signal retrieval, multimodal memory, spaced-repetition decay, and procedural learning. Rust core with Python, TypeScript, Go SDKs + MCP s…
jj-cheng25/weixin-articles-mcp
native (mp4 keyframes), Channels/视频号 (metadata + cover via public API).
SynthScope
A web search agent that enables you to search, visualize, and listen to information.
AI Job Hunting Agent
Checks for jobs continuously (24×7) on a schedule you control Parses job descriptions, extracts skills & keywords, and scores matches to your preferences Sends notifications (Em…
Codex Native Long Video Memory
Local-first Codex plugin that indexes long videos with OCR/ASR and answers with timestamped, SHA-verified visual evidence.
Deep Agent Real Estate
Bridging Generative AI and Classical ML. A production-grade multi-agent system using ReAct orchestration, MCP, A2A, and LMMs for hyper-local property valuation with Evals.
Aleph Docs
Multimodal documentation-aware LLM knowledge system: MCP server + pgvector semantic memory with Ebbinghaus forgetting curve + live 3D viewer. Embeds Markdown, images, video, audio…
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.
Advance Fraud Analyst
Multi-model fraud detector using Hugging Face + LangChain + MCP
Doc7
Convert any document—PDFs, Office files, scans, charts—into AI-ready Markdown for seamless search, quoting, and reasoning.
Knowdrive MCP
Multiplayer RAG for your private data: multimodal semantic search over you and your team's knowledge base — the corpus stays out of the conversation. Login to send invites and sha…
XaCodeApp
A powerful AI coding workspace for Windows with multiple models, autonomous tools, team mode, MCP, and vision support.
Chatgpt SDK Multimodal MCP App
ChatGPT Apps SDK Explained — Build Interactive AI Apps Inside ChatGPT Using MCP!
Strathmore School AI App Builders Program August Holidays 2026
August 2026 Holiday Program for www.strathmore.ac.ke students. A course on building AI apps for typical AI paradigms (e.g. Multimodal, RAG, tool use, AI agents, Text-to-SQL) using…
Be My Geminis
Routes every image Claude Code touches through Gemini Vision into typed JSON. Video, MCP, structured visual diff, and a quiet Opus fallback when Gemini's down.
Wechat Claude Assistant
Use WeChat as a worker-first remote task entry for local Claude Code, with optional advanced Channels mode and multimodal input support.
Langchain Chatchat
基于Langchain-Chatchat项目的v0.2.10版本维护，进行优化和个性化开发，对齐openai、支持多模态、工具管理和调用、文档对话、token计算和对接任意第三方智能体平台。
QuokkaAgent
基于 Streamlit 的多模态 AI Agent Demo
MyAIBOX
🧰 AI百宝箱 — a modular Gen-AI suite: 🤖 agent with tool use & MCP, 💬 multimodal chat, 📝 text processing, 🧠 deep reasoning, 👀 vision, 🎨 image generation & editing. FastAPI + React + AG…
Womens Fashion Catalog Open Data
Open dataset of 2,770+ curated women fashion products from Livostyle.com — weekly-synced. MIT. For LLM training, recommender systems, multimodal research.
LLM Projects Store
LLM Projects Store , production-ready LLM applications built using RAG, AI Agents, Multi-Agent Teams, MCP, Voice AI, and Multimodal systems
Looki Claude
首个公开的 Looki L1 × Claude 深度接入 skill 包。把你 Looki 里的每一秒,交给 Claude 读。零依赖 Python 客户端 + ffmpeg 视频抽帧 + 10 条踩坑录。
Clipmind
Local-first multimodal video evidence extraction for humans and AI agents. Paste a YouTube or Douyin link or drop a file; get transcript, OCR, visual states and a structured Evide…
MyCalPal
Multimodal calendar agent. Screenshot to a Discord bot, parsed into an editable draft, published to Google Calendar.
Sample To Make LLM Service
Sample code to make llm service