# openrouter-mcp-multimodal

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 Claude Desktop, Cur…

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y smithery mcp add stabgan/openrouter-mcp-multimodal

# Browse available tools
npx -y smithery tool list stabgan/openrouter-mcp-multimodal

# Get full schema for a tool
npx -y smithery tool get stabgan/openrouter-mcp-multimodal chat_completion

# Call a tool
npx -y smithery tool call stabgan/openrouter-mcp-multimodal chat_completion '{}'
```

## Tools (11)

- `chat_completion` — Send messages to an OpenRouter model and get a response. Supports provider routing (quantizations / ignore / sort / ord…
- `analyze_image` — Analyze an image using a vision model
- `analyze_audio` — Analyze or transcribe an audio file using a multimodal model
- `analyze_video` — Analyze or transcribe a video file using a multimodal model. Accepts mp4, mpeg, mov, or webm from a local file path, HT…
- `search_models` — Search available OpenRouter models
- `get_model_info` — Get details about a specific model
- `validate_model` — Check if a model ID exists
- `generate_image` — Generate an image from a text prompt. Optionally conditioned on one or more reference images (file paths, http(s) URLs,…
- `generate_audio` — Generate audio from a text prompt. Conversational models (e.g. openai/gpt-audio) respond in spoken audio. Music models …
- `generate_video` — Generate a video from a text prompt using an OpenRouter video-generation model (default: google/veo-3.1). Submits an as…
- `get_video_status` — Resume a previously submitted video generation job by id. Returns the latest status; if completed, downloads the video …

```bash
# Get full input/output schema for a tool
npx -y smithery tool get stabgan/openrouter-mcp-multimodal <tool-name>
```