OpenRouter MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENROUTER_API_KEY | Yes | Your OpenRouter API key (required) | |
| OPENROUTER_APP_NAME | No | Application name for API headers | |
| OPENROUTER_BASE_URL | No | API base URL | https://openrouter.ai/api/v1 |
| OPENROUTER_SITE_URL | No | Your site URL for API attribution |
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 | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_modelsB | Get list of available OpenRouter models |
| chat_with_modelB | Send a message to a specific OpenRouter model |
| compare_modelsC | Compare responses from multiple models |
| get_model_infoC | Get detailed information about a specific model |
| analyze_documentA | Analyze large documents using parallel processing with multiple model instances |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Available Models | List of all available OpenRouter models with pricing |
| Model Pricing | Current pricing information for all models |
| Usage Statistics | Your OpenRouter usage statistics |
TDQS
Scored across 5 tools
Each tool targets a distinct action: document analysis, chat, model comparison, model info retrieval, and listing. There is no overlap in purpose.
All tool names follow a consistent verb_noun pattern (e.g., analyze_document, chat_with_model), making the naming predictable and easy to understand.
Five tools is a concise yet comprehensive set for interacting with an AI model provider like OpenRouter. Each tool serves a clear role without unnecessary duplication.
The tools cover core operations (listing, info, chat, comparison, document analysis). A minor gap is the lack of streaming or parameter configuration options, but the set is functional for typical use cases.