Enterprise DNA
M MCP Servers Developer low

stabgan/openrouter-mcp-multimodal

by Various

MCP server for OpenRouter — chat with 300+ LLMs (Claude, Gemini, GPT), analyze images / audio / video, generate images / speech / music / video (Veo 3.1, Sora, Seedance, Wan) from

S

MCP

stabgan/openrouter-mcp-multimodal

Added 1 June 2026

#ai-agent #claude #claude-desktop #cursor #docker #gemini #image-generation #llm

Overview

An MCP server that connects to OpenRouter, enabling chat with 300+ LLMs including Claude, Gemini, and GPT. It also supports analysis of images, audio, and video, as well as generation of images, speech, music, and video (Veo 3.1, Sora, Seedance, Wan) from compatible clients like Claude Desktop, Cursor, Kiro, and VS Code.

Best for

Best for
Developers who need to switch between many LLMs and multimodal models from a single MCP-compatible client

Use cases

  • Chat with any OpenRouter model without switching APIs
  • Analyze images, audio, or video using a single MCP endpoint
  • Generate media (images, speech, music, video) from your editor or environment

How to use

Install

npx -y @stabgan/openrouter-mcp-multimodal

Tools exposed

  • chat_completion
  • analyze_image
  • analyze_audio
  • analyze_video
  • generate_image
  • generate_audio
  • generate_video
  • generate_video_from_image
  • get_video_status
  • search_models
  • get_model_info
  • validate_model
  • rerank_documents
  • health_check
  • OPENROUTER_API_KEY
  • OPENROUTER_DEFAULT_MODEL
  • OPENROUTER_INTEGRATION_MODEL
  • OPENROUTER_OUTPUT_DIR
  • OPENROUTER_INPUT_DIR
  • OPENROUTER_LOG_LEVEL

Tested with

Claude Desktop, Claude Code, Cursor, Windsurf, Cline, VS Code

Notes

An MCP server that connects to OpenRouter, enabling chat with 300+ LLMs including Claude, Gemini, and GPT. It also supports analysis of images, audio, and video, as well as generation of images, speech, music, and video (Veo 3.1, Sora, Seedance, Wan) from compatible clients like Claude Desktop, Cursor, Kiro, and VS Code.

42 stars on GitHub. Last updated 2026-06-01. Licensed Apache-2.0.

Use cases

  • Chat with any OpenRouter model without switching APIs
  • Analyze images, audio, or video using a single MCP endpoint
  • Generate media (images, speech, music, video) from your editor or environment

Pros

  • Unified interface to hundreds of models via MCP
  • Multimodal input and output support
  • Works with popular developer tools out of the box

Cons

  • Requires an OpenRouter API key and usage costs apply
  • Relies on OpenRouter availability and rate limits
  • Small community (42 stars) may mean limited support

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • Unified interface to hundreds of models via MCP
  • Multimodal input and output support
  • Works with popular developer tools out of the box

Cons

  • Requires an OpenRouter API key and usage costs apply
  • Relies on OpenRouter availability and rate limits
  • Small community (42 stars) may mean limited support
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

Running a business, not writing the code? See the MCP servers picked for operators, and get your first one wired up with us.

Operator picks