OpenRouter MCP Multimodal Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEFAULT_MODEL | No | Default model to use for chat completions (e.g., qwen/qwen2.5-vl-32b-instruct:free) | |
| OPENROUTER_API_KEY | Yes | Your OpenRouter API key from https://openrouter.ai/keys |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| mcp_openrouter_chat_completionC | Send a message to OpenRouter.ai and get a response |
| mcp_openrouter_analyze_imageC | Analyze an image using OpenRouter vision models |
| mcp_openrouter_multi_image_analysisC | Analyze multiple images at once with a single prompt and receive detailed responses |
| mcp_openrouter_analyze_audioB | Transcribe audio files and provide raw content. Supports wav/mp3 files from CDN URLs or local paths. |
| search_modelsC | Search and filter OpenRouter.ai models based on various criteria |
| get_model_infoC | Get detailed information about a specific model |
| validate_modelC | Check if a model ID is valid |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Most tools have distinct purposes targeting different resources or actions, such as analyzing audio vs. images vs. chat completions. However, 'mcp_openrouter_analyze_image' and 'mcp_openrouter_multi_image_analysis' could cause some confusion as both handle image analysis, though the multi-image variant is specialized for batch processing.
The naming is mixed: some tools use a consistent 'mcp_openrouter_' prefix for multimodal functions (e.g., 'mcp_openrouter_analyze_audio'), while others like 'get_model_info' and 'search_models' follow a simpler verb_noun pattern without the prefix. This inconsistency reduces predictability but remains readable.
With 7 tools, the count is well-scoped for a multimodal server focused on model interactions and analysis. It covers key areas like model management, chat, and various media analyses without being overwhelming or too sparse.
The toolset provides solid coverage for OpenRouter's multimodal capabilities, including model search/info, chat, and audio/image analysis. A minor gap is the lack of tools for video analysis or other media types, but core workflows are well-supported.