mrn-gemini-imagen-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_MODEL | No | Gemini model to use | gemini-3-pro-image-preview |
| GEMINI_API_KEY | Yes | Your Google Gemini API key | |
| GEMINI_OUTPUT_DIR | No | Output directory for images | ./generated_images |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_imageB | Generate an image from a text description using Google Gemini. Returns the file path of the generated image. |
| edit_imageA | Edit an existing image based on a text prompt using Google Gemini. Useful for modifying specific parts of an image while preserving others. |
| iterate_imageB | Iteratively refine an image through multi-turn conversation. Start a new session with an image, or continue an existing session to make incremental adjustments. |
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 3 tools
Each tool has a clear, distinct purpose: generate creates new images, edit modifies existing ones with a single prompt, and iterate enables multi-turn refinement. The descriptions make the boundaries unambiguous.
All tool names follow a consistent verb_noun pattern in snake_case (generate_image, edit_image, iterate_image), making them easy to understand and predict.
Three tools is an ideal size for this domain—covering creation, editing, and iterative refinement without redundancy or unnecessary bloat.
The tool surface fully covers the core image manipulation workflow: generate from scratch, edit with a prompt, and iteratively refine through conversation. No obvious gaps for the intended purpose.