Home › Design & Media › openrouter-mcp-multimodal
openrouter-mcp-multimodal
Chat with 300+ LLMs via OpenRouter. Analyze and generate images, audio, and video from MCP.
Topics: Multimedia Process
Connect
Review any command before running it. Package names and URLs come from the server's own registry entry.
Package (npm 4.5.1)
npx -y @stabgan/openrouter-mcp-multimodal@4.5.1
Or add to your MCP client config:
{
"mcpServers": {
"openrouter-mcp-multimodal": {
"command": "npx",
"args": [
"-y",
"@stabgan/openrouter-mcp-multimodal@4.5.1"
],
"env": {
"OPENROUTER_API_KEY": "<YOUR_VALUE>",
"OPENROUTER_DEFAULT_MODEL": "<YOUR_VALUE>",
"OPENROUTER_OUTPUT_DIR": "<YOUR_VALUE>",
"OPENROUTER_MAX_TOKENS": "<YOUR_VALUE>",
"OPENROUTER_PROVIDER_SORT": "<YOUR_VALUE>",
"OPENROUTER_PROVIDER_IGNORE": "<YOUR_VALUE>",
"OPENROUTER_PROVIDER_ORDER": "<YOUR_VALUE>",
"OPENROUTER_PROVIDER_QUANTIZATIONS": "<YOUR_VALUE>",
"OPENROUTER_PROVIDER_REQUIRE_PARAMETERS": "<YOUR_VALUE>",
"OPENROUTER_PROVIDER_DATA_COLLECTION": "<YOUR_VALUE>",
"OPENROUTER_PROVIDER_ALLOW_FALLBACKS": "<YOUR_VALUE>",
"OPENROUTER_CACHE_RESPONSES": "<YOUR_VALUE>",
"OPENROUTER_INCLUDE_REASONING": "<YOUR_VALUE>"
}
}
}
}
OPENROUTER_API_KEYrequired secret — OpenRouter API key. Get one free at https://openrouter.ai/keysOPENROUTER_DEFAULT_MODEL— Default model for chat + analyze tools. Defaults to nvidia/nemotron-nano-12b-v2-vl:free.OPENROUTER_OUTPUT_DIR— Sandbox root for save_path on generate_* tools. Defaults to the current working directory.OPENROUTER_MAX_TOKENS— Default max_tokens for chat_completion when unset in the request.OPENROUTER_PROVIDER_SORT— price / throughput / latencyOPENROUTER_PROVIDER_IGNORE— CSV of provider slugs to exclude.OPENROUTER_PROVIDER_ORDER— JSON array or CSV of preferred provider IDs.OPENROUTER_PROVIDER_QUANTIZATIONS— CSV of quantization levels (fp16,int8).OPENROUTER_PROVIDER_REQUIRE_PARAMETERS— true/false. Require providers to support all request params.OPENROUTER_PROVIDER_DATA_COLLECTION— allow/denyOPENROUTER_PROVIDER_ALLOW_FALLBACKS— true/falseOPENROUTER_CACHE_RESPONSES— Enable response caching server-wide. Sends X-OpenRouter-Cache: true on every chat/analyze call unless overridden per-request. Zero tokens billed on cache hits.OPENROUTER_INCLUDE_REASONING— Enable reasoning tokens passthrough server-wide. Adds _meta.reasoning to chat_completion responses for DeepSeek R1 / Gemini Thinking / Opus 4.7.
Package (oci)
docker run -i --rm docker.io/stabgan/openrouter-mcp-multimodal:4.5.1
Or add to your MCP client config:
{
"mcpServers": {
"openrouter-mcp-multimodal": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/stabgan/openrouter-mcp-multimodal:4.5.1"
],
"env": {
"OPENROUTER_API_KEY": "<YOUR_VALUE>"
}
}
}
}
OPENROUTER_API_KEYrequired secret — OpenRouter API key. Get one free at https://openrouter.ai/keys
Related servers
openshorts
Turn long videos into viral vertical shorts and publish them to TikTok, Instagram and YouTube.
Pixelle-MCP
An omnimodal AIGC framework that seamlessly converts ComfyUI workflows into MCP tools with zero code, enabling full-modal support for…
FableCut
Zero-dependency browser video editor AI agents drive via a JSON timeline over MCP; ffmpeg export.
imagesorcery-mcp
ComputerVision-based 🪄 sorcery of image recognition and editing tools for AI assistants.
guaardvark
Self-hosted AI studio exposing its local image, video, music-video and Film Crew generation, upscaling, RAG and code intelligence as MCP…
gflow-cli
Drive Google Flow from an agent: Veo video and Imagen image generation
Listed in punkpeye/awesome-mcp-servers (MIT)
Data from the Official MCP Registry