OpenRouter MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENROUTER_API_KEY | No | Optional API key for higher rate limits (200 req/min vs 20 req/min). Get your key at: 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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_modelsB | List models available on OpenRouter. Args: modality: Filter by output type. Options: text, image, audio, embeddings, all sort_by: Sort by: name, created, price, context_length |
| get_modelA | Get detailed info for one model. Args: model_id: Model slug, e.g. 'anthropic/claude-sonnet-4.6' |
| search_modelsA | Search and filter OpenRouter models. Args: query: Free-text search in model name/id/description provider: Filter by provider (anthropic, google, openai, etc.) max_input_price: Max input price per 1M tokens, 0 = no limit min_context: Minimum context window size requires_tools: Only models supporting tool calling requires_vision: Only models with vision/image input free_only: Only free models |
| compare_modelsB | Compare multiple models side by side. Args: model_ids: Comma-separated model IDs |
| refresh_cacheA | Force refresh the model cache from OpenRouter. |
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 5 tools
Each tool has a distinct purpose: get single model details, list with basic filters, search with advanced filters, compare multiple, and cache refresh. No overlapping functionality; descriptions clearly differentiate them.
All tool names follow a consistent verb_noun pattern using lowercase with underscores: list_models, search_models, get_model, compare_models, refresh_cache. No mixing of conventions.
With 5 tools, the server provides a focused set for model discovery and management. This is neither too few nor too many for the domain of querying model information from OpenRouter.
The tool set covers all essential operations for interacting with OpenRouter models: listing, searching, getting details, comparing, and cache management. No obvious gaps like missing model capability queries, as search covers those.