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.
-
—
-
—
MIT ★ 5 -
Local multimodal inference service
MIT ★ 5 -
Process and prepare your multimodal medical data with natural language!
-
PDF multimodal conversion MCP tool for Claude Code and Gemini CLI
npm MIT -
multimodal-reader-mcpupdated this year
FastMCP server for reading local audio and video files with Google Gen AI.
pypi -
MCP server for OpenRouter.ai with text and image support
npm Apache-2.0 -
Local-first, Agent-callable Evidence engine for documents and media, exposed through Python, CLI, and MCP.
MIT -
Multimodal PDF RAG over pgvector - text, tables and images through Azure OpenAI, exposed as FastAPI, Streamlit and an MCP server
MIT -
MCP server for Xiaomi MiMo multimodal understanding API (image, audio, video).
MIT -
multimodal_search_mcp_architecturegithub.com/estelacode/multimodal_search_mcp_architectureupdated this year
Low-Latency Multimodal Search Web App with MCP Architecture 🔌🛠️🧠 #StrandsAgentSDK #FasterWhisper #Multilingual #MultimodalSearch #ChromaDB # DockerCompose
★ 1 -
MCP server for OpenRouter providing text chat and image analysis tools
npm MIT -
MCP server for image generation and editing, speech recognition, text recognition, speech synthesis, voice design, video generation and multimodal media analysis.
pypi MIT -
@ajmalaksar/multimodal-mcpgithub.com/ajmalaksar25/multimodal-mcpupdated this year
MCP server and CLI exposing Google's multimodal models (Gemini AI Studio and Vertex AI) for image, video, and audio analysis plus image generation — for Claude Code and other agents.
npm MIT -
multimodal-mcpgithub.com/rsmdt/multimodal-mcpupdated this year
Multi-provider media generation MCP server. Generate images, videos, and audio from text prompts using OpenAI, xAI, and Gemini through a single unified interface.
npm MIT ★ 2 -
multimodal-music-intelligence-systemgithub.com/SriChandhana/multimodal-music-intelligence-systemupdated this year
Agentic AI system with custom MCP server orchestrating 7 AI tools across Spotify, MusicBrainz & ACRCloud — multimodal music intelligence (audio, text, image)
MIT ★ 2 -
@firstdoit/openrouter-mcp-multimodalgithub.com/firstdoit/openrouter-mcp-multimodalupdated this year
MCP server for OpenRouter providing text chat and image analysis tools (fixed stdio buffer handling)
npm MIT -
ai-driven-multimodal-analyticsgithub.com/serhatsoysal/ai-driven-multimodal-analyticsupdated this year
Enterprise-grade Multimodal AI Gateway leveraging FastAPI, OpenAI (GPT-4o, Whisper, TTS), and MCP Server architecture. Featuring asynchronous task processing, Redis caching, and real-time AI/ML pipeline orchestration.
MIT ★ 1 -
Native Model Context Protocol (MCP) server exposing HubX's mobile-first multimodal toolchain: vision diagnostics, voice transcription, photo-realistic generation, and spatial design.
MIT -
multimodal-embedding-mcp-servergithub.com/Hafizzowa/multimodal-embedding-mcp-serverupdated this year
Build a Local Multi-Modal AI Agent Memory Server Using Gemini Embeddings 2026
-
ai-multimodal-fraud-price-enginegithub.com/tncyavci/ai-multimodal-fraud-price-engineupdated this year
Multi-modal marketplace price valuation & scam detection engine (0-100 Trust Score) using Vision OCR, feature regression, and FastMCP
-
mcp-voice-assistant-and-multimodal-demogithub.com/mrzasad/mcp-voice-assistant-and-multimodal-demoupdated this year
A dual-lab AI project: Vault-AI – banking MCP server with LangGraph ReAct agent + Streamlit UI; Voice-AI-Bot – multimodal chatbot using Google Gemini and Speechmatics STT/TTS. Shared Python environment.
-
Agentic-Multimodal-Expense-Processinggithub.com/uditsanghvi07/Agentic-Multimodal-Expense-Processingupdated this year
Agentic Multimodal Expense Processing (AMEP): End-to-end GenAI pipeline using Multimodal LLMs for zero-shot data extraction from invoice images. Implements an Agentic MCP server for autonomous classification, transforming unstructured documents into structured expense reports in real-time Google Sheets for analytics.
-
multimodal-bridgegithub.com/Spirit4471/multimodal-bridgeupdated this year
Multimodal bridge for any LLM: qwen_vision (Qwen-VL) + qwen_generate (Qwen-Image) — an MCP server for Kimi Code & Claude Code, and a DeepSeek Harness plugin (dsh-multimodal-bridge). 给任何 LLM 补上 Qwen 视觉与出图能力:MCP server(Kimi Code / Claude Code)+ DeepSeek Harness 插件双形态。
MIT ★ 3 -
MCP server for OpenRouter — chat with 300+ LLMs (Claude, Gemini, GPT), analyze images / audio / video, generate images / speech / music / video (Veo 3.1, Seedance, Kling, Wan) from Claude Desktop, Cursor, Kiro, VS Code.
npm Apache-2.0 ★ 103 -
claude-gemini-multimodal-bridgegithub.com/goodaymmm/claude-gemini-multimodal-bridgeupdated this year
MCP bridge connecting Claude Code, Antigravity CLI and Google AI Studio, routing each request to the layer that can answer it: web search, complex reasoning, or image/audio/document processing
npm MIT -
Multimodal sensory grounding (Meta Ray-Ban audio/vision) integrated with long-term episodic life memory graphs and empathetic emotional resonance (Muse).
NOASSERTION ★ 2 -
多模态内容理解与工具编排 Agent:Chinese-CLIP 图文共享向量空间 + BM25/RRF 混合检索 + cross-encoder 重排(真实文本查询 hit@10 0.668→0.918)+ Schema 约束工具调用 + 可溯源生成,含 MCP、多轮会话记忆、ReAct 编排与分层离线评测。 | Multimodal agent: Chinese-CLIP retrieval, BM25+RRF hybrid search, cross-encoder reranking, schema-constrained tool calling, MCP server.
MIT -
Calypso Multimodal RAGno update data
Multimodal RAG for source-backed AI answers. Launch a hosted Gemini File Search RAG layer that answers from your PDFs, docs, screenshots, charts, diagrams, help center, FAQs, and images with citations people can verify. Calypso gives your website, AI agents, workflows, and product UI one reusable knowledge layer for grounded answers across text and visual content.
smithery -
MCP tool for multimodal image recognition
-
mimo-vision-mcpupdated this year
MCP server for visual understanding via Xiaomi MIMO multimodal API
pypi MIT -
llm-mcp-serverupdated this year
MCP server for LLM API with multimodal support (text, image, audio, video)
npm MIT -
A MCP server for video multimodal understanding based on Alibaba Cloud DashScope
pypi MIT -
tonyq-mimo-mcp-serverupdated this year
MCP Server for MiMo multimodal capabilities (image, audio, video understanding, ASR, TTS)
npm MIT -
@fre4x/geminiactive
A Gemini MCP server providing multimodal analysis and image/video generation.
npm MIT -
@iflow-mcp/morphik-org-mcpgithub.com/morphik-org/morphik-npm-mcpupdated this year
MCP server for Morphik multimodal database
npm ISC -
MCP server and library that help agents view and annotate multimodal data within a token budget
pypi Apache-2.0 -
vision-mcpgithub.com/okysu/vision-mcpupdated this year
MCP server providing multimodal vision capabilities via OpenAI-compatible APIs
npm MIT -
zhipu-glm-vision-mcpupdated this year
MCP server for GLM-4.6V-Flash multimodal understanding (image/video/file) via Zhipu API
pypi 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 -
Prism MCP: agent door for the Prism multimodal playground API (MIT).
npm MIT -
@xyzensun/visionmcpupdated this year
MCP stdio server for image understanding through configurable multimodal providers (OpenAI / Anthropic / Gemini formats).
npm MIT -
MCP server that reads images via SenseNova 6.8 Flash-Lite multimodal model
npm MIT -
Multimodal local search over documents and media — pdf, office files, notes, images, audio and subtitles — from any MCP-capable agent.
pypi MIT -
lookback-aiupdated this year
Local-first multimodal semantic memory for your machine — searchable text + screenshots, MCP-native, runs on CPU.
pypi MIT -
Digital Collections Explorer: The multimodal viewer for searching digital collections.
NOASSERTION ★ 16 -
Multimodal Media Understanding Infrastructure for AI Agents
Apache-2.0 -
Model Context Protocol (MCP) server for Lucid App integration with multimodal AI analysis
npm MIT -
Evidence-aware Bilibili video research MCP for language, vision, and multimodal analysis.
MIT ★ 18 -
MCP server for PowerPoint analysis and multimodal AI integration - comprehensive metadata extraction and slide image capture for agents
pypi MIT -
Zero-dependency MCP server for AI-powered SVG icon generation with multimodal LLM support
npm MIT -
Restaurant & recipe recommender with local LLMs: structured extraction, multimodal RAG (ChromaDB + CLIP), LangGraph agents and an MCP server with a Gradio host.
MIT -
@captain-sdk/captain-mcpgithub.com/runcaptain/captain-mcpupdated this year
MCP server for Captain — multimodal RAG search and live project search. Usable from Claude Code, Cursor, and any MCP-aware client.
npm MIT -
MCP server for Excel analysis and multimodal AI integration - comprehensive metadata extraction and sheet image capture for agents
pypi MIT -
🦌 Kancil — the clever agent that lives in your Messenger. Muse Spark brain + multimodal (text/photo/voice/video) + Ghostfox MCP eyes + persistent memory.
npm -
visionsearch-mcpgithub.com/tiagohgms/visionsearch-mcpupdated this year
Multimodal Web Intelligence MCP — local-first image, PDF, and document research via LM Studio
npm MIT -
A full-stack multimodal meeting intelligence system with layered RAG, long-term memory, and skill-based generation.
MIT ★ 4 -
Brigithub.com/Alexi5000/Briactive
BRI — empathetic video intelligence with production Streamlit, FastAPI MCP, SQLite durability, and multimodal ML tooling
MIT -
Give Claude the ability to watch and understand videos — Claude Code plugin with frame extraction and multimodal audio analysis
npm MIT ★ 1,512 -
@harrylabs/llm-knowledge-basesupdated this year
Representation-first multimodal Markdown wiki runtime for Obsidian vaults, with standalone CLI, MCP server, and OpenClaw compatibility.
npm MIT