# stabgan/openrouter-mcp-multimodal [Health: Active]

**Category:** 🎥 Multimedia Process  
**Repository:** https://github.com/stabgan/openrouter-mcp-multimodal  
**GitHub Stars:** 86  
**npm Downloads (last month):** 6915  
**Views:** 4  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/stabgan-openrouter-mcp-multimodal

## Description
All-in-one multimodal MCP for 300+ OpenRouter models: text chat, image / audio / video analysis, and image / audio / video generation (Veo 3.1, Sora 2 Pro, Seedance, Wan). Structured meta.code error taxonomy, IPv4+IPv6 SSRF guards, path-sandbox for disk writes, retry-after-aware backoff, multi-arch Docker.

## Tools
Capabilities this server exposes over MCP:

- **chat_completion** — Text chat, web search, provider routing, caching, reasoning
- **start_chat_completion** — Async background job for long-running reasoning models
- **get_chat_completion_status** — Poll / retrieve async completion results
- **analyze_image** — Vision — local path, URL, or data URL + `question
- **analyze_audio** — Transcribe / analyze audio files
- **analyze_video** — Describe / Q&A over video files
- **generate_image** — Text-to-image via chat completions with reference images
- **generate_image_dedicated** — Text-to-image via dedicated `/api/v1/images` (resolution, quality, format)
- **generate_audio** — Text-to-speech / music via chat completions
- **text_to_speech** — Dedicated TTS (`/api/v1/audio/speech`) — free Deepgram default, voices, speed, mp3/pcm
- **speech_to_text** — Dedicated STT (`/api/v1/audio/transcriptions`) — Whisper, GPT-4o
- **generate_video** — Text-to-video (async, resumable)
- **generate_video_from_image** — Image-to-video (narrower schema)
- **get_video_status** — Poll / resume video jobs
- **search_models** — Paginated model catalog search
- **get_model_info** — Pricing, context, modalities
- **validate_model** — Cheap model ID existence check
- **rerank_documents** — Relevance ranking for RAG
- **health_check** — API key + reachability probe

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "openrouter-mcp-multimodal": {
    "command": "npx",
    "args": ["-y","@stabgan/openrouter-mcp-multimodal"],
    "env": {
      "OPENROUTER_API_KEY": ""
    }
  }
}
```

**Requires environment variables:** `OPENROUTER_API_KEY` — the values above are empty placeholders; fill in real credentials before running (see the repository for what each one is for).

## Documentation

## What stabgan/openrouter-mcp-multimodal MCP server does

The stabgan/openrouter-mcp-multimodal MCP server gives MCP-compatible agents access to OpenRouter's model catalog and multimodal API. Its tools cover ordinary text completion, vision questions, audio transcription and analysis, video understanding, and media generation. It also includes supporting operations for finding models, checking model IDs, reading pricing and modality metadata, reranking documents, and probing API availability.

The server is suited to agents that need to choose among many OpenRouter models rather than connect to one fixed provider. Chat requests can use provider routing, web search, response caching, reasoning options, and OpenRouter model suffixes such as `:free`, `:online`, or `:exacto`, where supported by the selected model.

## How it works

The stabgan/openrouter-mcp-multimodal MCP server runs locally over stdio and forwards supported requests to OpenRouter. A client invokes an MCP tool with a model and task-specific inputs. Image analysis accepts a local path, URL, or data URL; audio and video tools work with files. Image, audio, and video generation return media-related results through the corresponding generation tools.

Long-running work is handled with separate lifecycle tools. Chat jobs can be started in the background, checked for status, and retrieved later. Video generation supports asynchronous polling and resumption, while video progress notifications are available for supported workflows. Dedicated endpoints are provided for image generation, text-to-speech, and speech-to-text in addition to chat-completion-based media operations.

## Setup and configuration

Install the Node.js package with `npx` and provide an OpenRouter API key through `OPENROUTER_API_KEY`:

```bash
export OPENROUTER_API_KEY=sk-or-v1-...
npx -y @stabgan/openrouter-mcp-multimodal
```

The README specifies Node.js 22 or newer for the Node installation. Add the resulting stdio server to an MCP client configuration. Cursor, Claude Desktop, VS Code, Windsurf, and Cline are listed as compatible clients. OpenRouter's free tier and free models can be used for some chat and vision requests, while audio and video generation typically require credits.

## Tools and capabilities

The stabgan/openrouter-mcp-multimodal MCP server exposes tools for:

- Text chat, including synchronous and asynchronous completion flows.
- Image questions and image generation with optional reference images.
- Audio analysis, transcription, speech synthesis, and music generation.
- Video description or question answering, plus text-to-video and image-to-video generation.
- Model catalog search, model details, model ID validation, and API health checks.
- Document relevance reranking for retrieval-augmented generation workflows.

Dedicated audio tools support text-to-speech voice, speed, and format options, as well as speech-to-text with Whisper or GPT-4o Transcribe. Dedicated image generation supports resolution, quality, and format controls.

## Limitations and notes

The server requires an OpenRouter API key even when using free models. Model capabilities, pricing, provider availability, and supported media formats depend on OpenRouter and the selected model. Generation tasks, particularly audio and video, may need account credits and may run asynchronously.

Local file handling includes path-sandbox protections, and network access includes IPv4 and IPv6 SSRF guards. Errors use structured metadata including a `meta.code` taxonomy. These safeguards do not remove the need to select models and inputs that match the intended modality.

_Full upstream README: https://allmcps.com/mcp/stabgan-openrouter-mcp-multimodal/readme_