Openrouter Multimodal
A unified multimodal bridge to OpenRouter's 300+ model catalog. Exposes six tools: chat_completion for text generation with provider routing and response caching, analyze_image/audio/video for understanding media files or URLs, and generate_image/audio for creation workflows. The video analysis tool handles mp4, mov, and webm formats, while video generation taps models like Veo 3.1 and Sora 2 Pro. Image inputs get sharp optimization automatically. Audio generation wraps raw PCM in WAV containers. Works with Claude Desktop, Cursor, VS Code, Windsurf, Cline, and Kiro. You'd reach for this when you need vision, speech, or video capabilities without juggling multiple API clients or when OpenRouter's per-request model switching matters more than provider lock-in.
- GitHub stars
- 45
- tools
- 21
- auth
- Secret needed
- transport
- STDIO
- env vars
- 13
- last updated
- May 4, 2026
Tools
21 toolsPublic tool metadata for what this MCP can expose to an agent.
chat_completionText chat, web search, provider routing, caching, reasoning, structured output
Text chat, web search, provider routing, caching, reasoning, structured output
No parameter schema in public metadata yet.
start_chat_completionAsync background job for long-running reasoning models
Async background job for long-running reasoning models
No parameter schema in public metadata yet.
get_chat_completion_statusPoll / retrieve async completion results
Poll / retrieve async completion results
No parameter schema in public metadata yet.
analyze_imageVision — local path, URL, or data URL + question
Vision — local path, URL, or data URL + question
No parameter schema in public metadata yet.
analyze_audioTranscribe / analyze audio files
Transcribe / analyze audio files
No parameter schema in public metadata yet.
analyze_videoDescribe / Q&A over video files
Describe / Q&A over video files
No parameter schema in public metadata yet.
generate_imageText-to-image via chat completions with reference images
Text-to-image via chat completions with reference images
No parameter schema in public metadata yet.
generate_image_dedicatedText-to-image via dedicated /api/v1/images (resolution, quality, format)
Text-to-image via dedicated /api/v1/images (resolution, quality, format)
No parameter schema in public metadata yet.
generate_audioText-to-speech / music via chat completions
Text-to-speech / music via chat completions
No parameter schema in public metadata yet.
text_to_speechDedicated TTS (/api/v1/audio/speech) — Deepgram, ElevenLabs, OpenAI; voices, speed, mp3/pcm
Dedicated TTS (/api/v1/audio/speech) — Deepgram, ElevenLabs, OpenAI; voices, speed, mp3/pcm
No parameter schema in public metadata yet.
speech_to_textDedicated STT (/api/v1/audio/transcriptions) — Whisper, GPT-4o Transcribe, Voxtral, ElevenLabs Scribe
Dedicated STT (/api/v1/audio/transcriptions) — Whisper, GPT-4o Transcribe, Voxtral, ElevenLabs Scribe
No parameter schema in public metadata yet.
generate_videoText-to-video (async, resumable)
Text-to-video (async, resumable)
No parameter schema in public metadata yet.
generate_video_from_imageImage-to-video (narrower schema)
Image-to-video (narrower schema)
No parameter schema in public metadata yet.
get_video_statusPoll / resume video jobs
Poll / resume video jobs
No parameter schema in public metadata yet.
search_modelsPaginated model catalog search
Paginated model catalog search
No parameter schema in public metadata yet.
get_model_infoPricing, context, modalities
Pricing, context, modalities
No parameter schema in public metadata yet.
validate_modelCheap model ID existence check
Cheap model ID existence check
No parameter schema in public metadata yet.
rerank_documentsRelevance ranking for RAG
Relevance ranking for RAG
No parameter schema in public metadata yet.
embed_textVector embeddings (37+ models: text-embedding-3-small/large, Nomic, etc.)
Vector embeddings (37+ models: text-embedding-3-small/large, Nomic, etc.)
No parameter schema in public metadata yet.
decideStructured decisions with calibrated probabilities (System One models)
Structured decisions with calibrated probabilities (System One models)
No parameter schema in public metadata yet.
health_checkAPI key + reachability probe
API key + reachability probe
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
OPENROUTER_API_KEY*secretOpenRouter API key. Get one free at https://openrouter.ai/keys
OPENROUTER_DEFAULT_MODELDefault model for chat + analyze tools. Defaults to nvidia/nemotron-nano-12b-v2-vl:free.
OPENROUTER_OUTPUT_DIRSandbox root for save_path on generate_* tools. Defaults to the current working directory.
OPENROUTER_MAX_TOKENSDefault max_tokens for chat_completion when unset in the request.
OPENROUTER_PROVIDER_SORTprice / throughput / latency
OPENROUTER_PROVIDER_IGNORECSV of provider slugs to exclude.
OPENROUTER_PROVIDER_ORDERJSON array or CSV of preferred provider IDs.
OPENROUTER_PROVIDER_QUANTIZATIONSCSV of quantization levels (fp16,int8).
OPENROUTER_PROVIDER_REQUIRE_PARAMETERStrue/false. Require providers to support all request params.
OPENROUTER_PROVIDER_DATA_COLLECTIONallow/deny
OPENROUTER_PROVIDER_ALLOW_FALLBACKStrue/false
OPENROUTER_CACHE_RESPONSESEnable 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_REASONINGEnable reasoning tokens passthrough server-wide. Adds _meta.reasoning to chat_completion responses for DeepSeek R1 / Gemini Thinking / Opus 4.7.
Readme
OpenRouter MCP Multimodal — MCP server for chat, vision, audio, and video AI tools
OpenRouter MCP Multimodal
The MCP server for multimodal AI agents.
One install · 21 tools · 300+ OpenRouter models · text, vision, audio & video — analysis and generation.
Details
- Repository
- github.com/stabgan/openrouter-mcp-multimodal
- Categories
- Communication & Messaging, Media & Entertainment
- Package
@stabgan/openrouter-mcp-multimodal- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
More from stabgan
Related Communication & Messaging MCP servers
View all
ContrastAPIupinar/contrastapi55 tools, 7 Resources, Sigma rules, email SPF/DMARC, MITRE, CVE/KEV, risk_score. No key.36stars
kernelCADw1ne/kernelcad-webCAD in ChatGPT and Claude: editable parts, STEP/STL/drawings, in-chat 3D, automatic checks.0stars
Geminihoutini-ai/gemini-mcpModel Context Protocol server for Google Gemini AI with chat, research, and grounding34stars
Cursor Historys2thend/cursor-history-mcpMCP server for browsing, searching, exporting, and backing up your Cursor AI chat history33stars
Deepseekarikusi/deepseek-mcp-serverMCP server for DeepSeek AI with chat, reasoning, sessions, function calling, and cost tracking26stars