- 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.
GLOBAL Old Firm RAG Query
v2: Hybrid (BM25+vector) legal RAG over a 145-matter law firm archive with OCR'd scans readable in-chat — Gemini Embedding 2, LanceDB, Cloud Run, MCP, queryable from Claude.ai wit…
Nexa Core
High-performance Rust runtime for hyperdimensional computing, holographic memory, and encoded-space AI inference.
Verifiable Deep Research Harness
可验证的Deep Research Agent Harness，支持多智能体协作、长程检索、证据溯源、引用核验、断点恢复、多模态输入与可复现评测。Verification-centric Deep Research Agent Harness with multi-agent orchestration, long-horizon retrieval, e…
Claude Code Eyes
Enable Claude Code to view and debug hardware via camera input for automated firmware, display, and UI verification.
Video Montage
Automate product demo voiceovers by generating timed narration from screen recordings using local browser-based video editing.
Spray Anything
Transform images into realistic spray paint effects using Python and JavaScript without requiring Photoshop or complex tools.
Oai Chat
Multi-modal Chatbot based on OpenAI
SperaxOS AI Agents
Specialized AI agents for DeFi, crypto, blockchain, Web3, DeFAI. Deep expertise in yield optimization, smart contracts, portfolio management. Multi-agent collaboration (Agent Team…
Vision Augment
本地优先的多模态视觉 MCP —— 为无视觉 LLM（DeepSeek、GLM 等）提供可自定义端点的看图 / OCR / 文档解析能力。
Zhipu Vision MCP
智谱视觉 MCP Server — 为 DeepSeek 等纯文本模型提供免费视觉能力（GLM-4V）
Vision Kit
Make your AI agent a math tutor. Structured extraction of vectors, matrices & geometry from math figures, with dimension-consistency + geometric self-check. Vision plugins for Dee…
Metachlorian
Self-hosted, shot-level video search for AI agents and editors. MCP server, semantic search, B-roll finder, exports to OTIO, FCPXML and EDL.
Multimodal Pdf Rag
Multimodal PDF RAG over pgvector - text, tables and images through Azure OpenAI, exposed as FastAPI, Streamlit and an MCP server
Foveal
Multimodal working memory for agents: perceive each image once, reference it cheaply, zoom in only when needed and share what was learned across sub-agents.
Nyaya Evidence Grounded Multimodal Claim Resolution Agent
Evidence-grounded multimodal claim resolution agent: LangGraph, CNN, deterministic policy engine, grounded LLM briefs, durable resume, CI-gated evals
Advance Fraud Analyst
Multi-model fraud detector using Hugging Face + LangChain + MCP
Codex Image Context Runtime
A Codex plugin and local MCP runtime for context-bounded image generation and inspection.
Docker MCP
🔧 Manage Docker containers for AI assistants effortlessly with the Model Context Protocol server, enabling seamless interactions without configuration.
NAS Agent Butler
基于 MCP 协议与多模态大模型的私有云/家庭 NAS 全能智能管家。零端口暴露、免公网 IP，支持对话/语音/拍照诊断、Docker 运维治理与生活晨报。
Bri
BRI — empathetic video intelligence with production Streamlit, FastAPI MCP, SQLite durability, and multimodal ML tooling
Libre
FrankX LibreChat workspace for self-hosted multimodal AI chat, agents, tools, model routing, and MCP-enabled assistants.
Connoisseur Companion
Restaurant & recipe recommender with local LLMs: structured extraction, multimodal RAG (ChromaDB + CLIP), LangGraph agents and an MCP server with a Gradio host.
Botanswer Architecture
AI receptionist and business-operations platform for LINE Official Accounts. Public architecture overview; source is private.
Cn LLM Bridge
No description published.
Dsh Eye Upload
No description published.