openrouter-imgen-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENROUTER_API_KEY | Yes | Your OpenRouter API key (required). Can also be passed via --api-key flag. | |
| OPENROUTER_IMG_CACHE_TTL | No | Cache TTL in milliseconds (default 5 minutes). Can also be set via --cache-ttl flag. | 300000 |
| OPENROUTER_IMG_LOG_LEVEL | No | Log level (e.g., warn, info, debug). Can also be set via --log-level flag. | warn |
| OPENROUTER_IMG_DEFAULT_MODEL | No | Default model for image generation. Can also be set via --default-model flag. | google/gemini-3-pro-image-preview |
| OPENROUTER_IMG_BATCH_CONCURRENCY | No | Maximum number of concurrent batch operations. Can also be set via --batch-concurrency flag. | 3 |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_image_modelsB | List available image generation models from OpenRouter with pricing and capabilities. |
| generate_imageA | Generate an image from a text prompt via OpenRouter. Supports quality presets (fast/balanced/quality) or explicit model IDs. For best results, expand brief prompts with details about composition, lighting, color palette, and mood before calling — unless the user explicitly asked for a simple/minimal prompt. |
| edit_imageB | Edit or transform existing images using a text prompt and reference images. Supports local file paths, URLs, and data URIs. For best results, expand brief prompts with details about composition, lighting, color palette, and mood before calling — unless the user explicitly asked for a simple/minimal prompt. |
| batch_imagesB | Generate or edit multiple images in a single call with concurrency control. Each task can be a generation (prompt only) or edit (prompt + reference images). |
| check_balanceA | Check your OpenRouter account balance — shows total credits, usage, and remaining balance. |
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: listing models, generating, editing, checking balance, and batching. The only mild overlap is batch_images, which subsumes both generate_image and edit_image, so an agent might occasionally debate between batch and single-call tools.
All five tools follow a clean verb_noun snake_case pattern (list_image_models, generate_image, edit_image, check_balance, batch_images). The convention is applied uniformly with no style deviations.
Five tools is well-scoped for an image generation/editing server, covering discovery, generation, editing, batching, and account state without redundancy. Each tool clearly earns its place.
The surface covers the core lifecycle: model discovery, single and batch generation, editing, and balance checking. Minor gaps like image upscaling, variation, or history/retrieval operations are absent but not essential to the stated purpose.