- 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.
agent-infra/mcp-server-browser
🤖 Community fork of ByteDance UI-TARS-desktop | Multimodal AI Agent with Chat System, Message Actions, Global Shortcuts & Optimization Settings | 基于字节跳动 UI-TARS-desktop 的社区增强版，新增聊…
mediar-ai/screenpipe
run agents that work for you in the background based on what you do
Multimodal Agents Course
An MCP Multimodal AI Agent with eyes and ears!
MCP
Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google
AI
🤖 Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps across OpenAI, Anthropic, Gemini, React, Vue, Svelte, and Solid.
Genkitx
A Genkit plugin that provides interoperability between Genkit and Model Context Protocol (MCP). Both client and server use cases are supported.
SimpleMem
[ICML'26] SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal
Shadow
Your computer was paying attention the whole time. 14-modality capture. Proactive intelligence. Computer-use training data. Native macOS. All on-device. Open source.
jcdickinson/simplemem
[ICML'26] SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal
Morphik Core
The most accurate document search and store for building AI apps
Pixeltable
Data Infrastructure providing a declarative, incremental approach for multimodal AI workloads.
mediar-ai/screenpipe
aware AI agents through a NextJS plugin ecosystem.
AI Agent Book
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
DataDesigner
🎨 NeMo Data Designer: A general library for generating high-quality synthetic data from scratch or based on seed data.
Openclaw.net
Self-hosted OpenClaw gateway + agent runtime in .NET (NativeAOT-friendly)
Claude Video Vision
Give Claude the ability to watch and understand videos — Claude Code plugin with frame extraction and multimodal audio analysis
Awesome Gemini Omni API Prompts
Curated Google Gemini Omni prompts & API examples — text-to-video, image-to-video, video edit via the Gemini Omni API on muapi.ai. Python wrapper, MCP server, REST examples.
ScreenMind
AI-powered screen memory — captures, analyzes, and lets you search/chat your screen history. Powered by Gemma 4 . 100% local, 100% private.
Watch Skill
Give any AI agent the ability to watch video — and to watch its own work and fix it. MCP + CLI + REST; scene-aware frames, OCR, local-first transcription, persistent index, and TH…
Codex Image Context Runtime
A Codex plugin and local MCP runtime for context-bounded image generation and inspection.
Dsh Crew
DeepSeek Harness (DSH) plugin: dispatch work to DSH agents from Claude Code / Codex — native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bri…
Noobot
Self-hosted AI agent workspace with tool calling, MCP, multi-model routing, sandboxed execution, multi-agent workflows, and LLM-authored 3D character animation rendered with Three…
Shadow
Your computer was paying attention the whole time. 14-modality capture. Proactive intelligence. Computer-use training data. Native macOS. All on-device. Open source.
Cortex
Open-source AI backend control plane for model routing, agent tools, OpenAI-compatible APIs, and private workspaces.
Achatbot
An open source chat bot architecture for voice/vision (and multimodal) assistants, local(CPU/GPU bound) and remote(I/O bound) to run.
Way Back Home
🚀 Way Back Home
Facio
A proactive AI agent for secure, traceable, human-in-the-loop task execution over long-running workflows.
Context Runtime
Context Runtime — a database query planner for LLM context. Decides what a model sees before it answers; plans it, runs it through reused substrate, and learns from the outcome.
LodeDB
World's fastest and most compact embedded vector database: exact by default, multimodal, local-first, and GPU-accelerated
Heliox OS
Open-source, local-first desktop AI agent for voice, gesture, gaze, browser and system automation with permission gates and verification.
ATLAS
Universal MCP server for logistics. Connect any TMS/WMS to AI agents. Shipments, carriers, tenders, tracking — all via Model Context Protocol.
LingShu
Apache-2.0, model-agnostic macOS agent: bring your own model to deliver verified code, docs, slides, and computer actions.
Genpark Infinite Canvas Spatial Clustering Synthesizer Skill
Infinite whiteboard spatial clustering engine & theme aggregator (Miro Assist)
AgentRunKit
Lightweight Swift 6 framework for building LLM-powered agents — cloud + on-device inference via MLX on Apple Silicon
OPSIE
OPSIIE (OPSIE) is an advanced Self-Centered Intelligence (SCI) prototype that represents a new paradigm in AI-human interaction.
Weilink
Zero-dependency Python SDK for WeChat Bot (iLink protocol) — text, image, video messaging & MCP server | 零依赖微信机器人 Python SDK，支持多媒体消息和 MCP 服务器
Mmx MCP Server
A unified Model Context Protocol server for MiniMax CLI (mmx)
Fortemi
Self-hosted AI knowledge base with hybrid semantic search (pgvector + FTS + RRF), MCP server, multi-provider LLM inference (Ollama, OpenAI, OpenRouter, llama.cpp), multimodal inge…
Raganything
API/MCP wrapper for RagAnything
Ia Na Pratica
IA na Prática: LLM, RAG, MCP, Agents, Function Calling, Multimodal, TTS/STT e mais
Conferllm
A CLI, Agent Skill, and MCP server for consulting AI models with persistent conversations and image support.
Clopinette AI
Cloudflare-native AI agent — 13 tools, codemode, 5-layer memory, self-learning, multimodal I/O. Telegram, Discord & WhatsApp bots. Web search, image gen, TTS, document RAG, calend…
Pdfvision
CLI, MCP server, and TypeScript library that extracts text, layout, and page images from PDFs for AI agents — when extraction goes wrong, it says so per page and says what to do n…
EagleRAG
Search knowledge by what documents mean and how they look — not one or the other.
Franken Surveillance System
Pure-Rust, evidence-native, local-first sensor fabric and semantic control plane for owner-authorized cameras and capture drones
Xiaohongshu Content Collector
Chrome 扩展:小红书/RedNote 笔记被动采集 + 多模态 AI 分析(爆款拆解·仿写·标签建议·视觉诊断) + 多格式/训练集导出,本地存储,内置防风控。支持 OpenRouter/Qwen 等模型列表一键刷新。
Visbridge
Token-efficient vision capability layer for MCP clients (describe / OCR / inspect)
Apiz
MCP (Model Context Protocol) server for apiz.ai — exposes generate / get_result / search_models / guide / account / speak / parse_video / transfer_url tools
Media Pipeline MCP Server
MCP server exposing 30+ media operations via StreamableHTTP — provider routing, cost tracking, pipeline execution
LLM Vision
A TypeScript MCP server that gives text-only LLMs image understanding through StepFun vision models.