Log inSubmit server
Openrouter MCP Multimodal logo

Openrouter MCP Multimodal

by stabgan

Routes chat, vision, audio, video, embeddings, and model utilities through OpenRouter using MCP.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Openrouter MCP Multimodal

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "stabgan-openrouter-mcp-multimodal": {
      "command": "npx",
      "args": [
        "-y",
        "@stabgan/openrouter-mcp-multimodal"
      ],
      "env": {
        "OPENROUTER_API_KEY": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

stabgan/openrouter-mcp-multimodal connects MCP-compatible coding agents to OpenRouter’s unified API over stdio. It exposes tools for chat, image/audio/video analysis and generation, embeddings, reranking, model discovery, structured decisions, and health checks across 300+ OpenRouter models. Long-running chat and video operations can run asynchronously with status polling, while local file access is protected by path sandboxing and remote requests by SSRF guards. Reach for it when an agent needs several multimodal AI operations without separate MCP servers for each media type.

Use cases

  • Analyze images, audio recordings, and video clips from an AI coding agent
  • Generate images, speech, music, and videos through OpenRouter
  • Search and validate models before selecting one for a task
  • Create embeddings and rerank documents for retrieval pipelines
  • Run asynchronous reasoning or video jobs and poll their results

Key features

  • Multimodal chat, vision, audio, and video tools
  • Image, audio, and video generation
  • Asynchronous chat and video job handling
  • Model search, inspection, and validation
  • Embeddings, document reranking, and structured decisions
  • SSRF guards, path sandboxes, and structured errors

Tools21

What Openrouter MCP Multimodal lets your agent do. Expand a tool for its parameters.

Self-reported~337 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

16/17 checks healthy over the last 78d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 8d ago via OSV.dev · @stabgan/openrouter-mcp-multimodal (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars101Stargazers on the source repository.
npm downloads1.6kPackage downloads in the last 30 days.
Last commit1d agoMost recent push to the default branch.
Tools exposed21Callable tools this server registers over MCP.
Directory activity8 viewsConfig copies, upvotes, and views on AllMCPs.

How Openrouter MCP Multimodal works

What stabgan/openrouter-mcp-multimodal MCP server does

OpenRouter MCP Multimodal gives MCP clients a single stdio connection to OpenRouter’s model catalog and API. Its 21 tools cover conversational completion, image understanding and creation, audio transcription and synthesis, video analysis and generation, embeddings, document reranking, model lookup, structured decisions, and service checks.

The chat tools support ordinary and reasoning-oriented requests, provider routing, web search, response caching, structured JSON output, and model suffixes such as :free, :online, :nitro, :floor, and :exacto. Vision tools accept local paths, URLs, or data URLs for image analysis. Audio and video tools handle file analysis, while generation tools cover images, speech, music, and video.

How it works

The server forwards requests to OpenRouter, which provides access to more than 300 models. Use chat_completion for a direct result, or start a background request with start_chat_completion and retrieve it using get_chat_completion_status. Video generation follows a similar asynchronous pattern with generate_video, generate_video_from_image, and get_video_status.

Dedicated media endpoints are available where OpenRouter exposes them. generate_image_dedicated supports image resolution, quality, and format controls. text_to_speech uses the dedicated speech endpoint with provider options including Deepgram, ElevenLabs, and OpenAI, while speech_to_text supports transcription providers such as Whisper, GPT-4o Transcribe, Voxtral, and ElevenLabs Scribe.

Setup and configuration

The server runs on Node.js 22 or newer. Set an OpenRouter API key and launch the package with npx:

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

Add the resulting stdio server to an MCP client’s mcpServers configuration. The documented clients include Cursor, Claude Desktop, VS Code, Windsurf, and Cline. Cursor supports project or user configuration; VS Code supports workspace or user configuration; Claude Desktop uses its platform-specific application configuration file.

The package is distributed through npm, with Python and Docker package listings also available. Free OpenRouter models can be used for chat and vision, while audio and video generation commonly require account credits.

Tools and capabilities

  • Run synchronous or asynchronous chat completions with reasoning, provider routing, web search, caching, and structured output.
  • Inspect images, audio, and video, including image questions and audio transcription.
  • Create images, speech, music, and videos, including image-to-video jobs.
  • Search, inspect, and validate OpenRouter model identifiers and retrieve pricing, context, and modality details.
  • Generate embeddings with more than 37 embedding models and rerank documents for retrieval workflows.
  • Produce structured decisions with calibrated probabilities and check API reachability with health_check.

Limitations and notes

Media capabilities depend on the selected OpenRouter model and provider. Long-running reasoning and video requests require asynchronous polling or resumption. Video and audio generation may require credits even when free models are available for chat and vision. Local file operations are constrained by path sandboxes, and remote resource access includes SSRF protections. Errors use structured metadata including a meta.code classification.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Openrouter MCP Multimodal

stabgan/openrouter-mcp-multimodal is an MCP server that connects compatible AI clients to OpenRouter’s unified model API. Its main tools handle chat completions, image, audio, and video analysis or generation, plus embeddings, model discovery, document reranking, structured decisions, and health checks.

Set `OPENROUTER_API_KEY`, then run `npx -y @stabgan/openrouter-mcp-multimodal`. Add the resulting stdio server to your client’s `mcpServers` configuration. The documented clients include Cursor, Claude Desktop, VS Code, Windsurf, and Cline.

Yes, it works with Cursor over stdio. Add the server to a project `.cursor/mcp.json` file or configure it through Cursor Settings → MCP, using the `mcpServers` configuration shape.

Yes, video generation is asynchronous. Use `generate_video` or `generate_video_from_image`, then poll or resume the job with `get_video_status`; video progress notifications are supported.

Related MCP servers

All in Multimedia Process All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewOpenrouter MCP Multimodal AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/stabgan-openrouter-mcp-multimodal?style=directory)](https://allmcps.com/mcp/stabgan-openrouter-mcp-multimodal)
HTML Embed
<a href="https://allmcps.com/mcp/stabgan-openrouter-mcp-multimodal"><img src="https://allmcps.com/api/badge/stabgan-openrouter-mcp-multimodal?style=directory" alt="Openrouter MCP Multimodal on AllMCPs" /></a>