# Multimodal

> Browse 5 items tagged with Multimodal.

## Items

- [multimodal-mcp-client](https://mcpserver.ever.works/ja/items/multimodal-mcp-client) — A multi-modal MCP client designed for voice-powered agentic workflows, enabling AI agents to process and interact with multiple media types through the Model Context Protocol.
- [Google Gemini MCP Server](https://mcpserver.ever.works/ja/items/google-gemini-mcp-server) — MCP server for Google Gemini supporting multimodal tasks across text, code, and images. Integrations produce design briefs, test plans, and visual analyses for rapid artifact-to-action conversion. Ideal for product and QA groups in fast feedback cycles.
- [OpenRouter MCP Multimodal](https://mcpserver.ever.works/ja/items/openrouter-mcp-multimodal) — MCP server for OpenRouter providing text chat and image analysis tools, enabling AI assistants to leverage multimodal capabilities through various LLM providers via OpenRouter.
- [Jina AI Embeddings MCP Server](https://mcpserver.ever.works/ja/items/jina-ai-embeddings-mcp-server) — Remote Model Context Protocol server providing access to Jina's multimodal embeddings, Reader API, and reranker capabilities. Features jina-embeddings-v4, a 3.8B parameter model that embeds text and images through a unified pathway for search and RAG applications.
- [Amazon Bedrock Data Automation MCP Server](https://mcpserver.ever.works/ja/items/amazon-bedrock-data-automation-mcp-server) — An MCP server for Amazon Bedrock that automates analysis of documents, images, videos, and audio files, providing multimodal content processing through MCP-compatible agents.

---

_Canonical page: https://mcpserver.ever.works/ja/tags/multimodal_