Gemini Image Generator MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | Yes | Your Google Gemini API key | |
| OUTPUT_IMAGE_PATH | Yes | Path to the folder where generated images will be saved |
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 |
|---|---|
| generate_image_from_textA | Generate an image based on the given text prompt using Google's Gemini model. |
| transform_image_from_encodedA | Transform an existing image based on the given text prompt using Google's Gemini model. |
| transform_image_from_fileA | Transform an existing image file based on the given text prompt using Google's Gemini model. |
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
The three tools have distinct purposes: one generates images from text, while the other two transform existing images but differ in input method (encoded data vs. file path). There is minor overlap between the two transform tools, as they serve similar functions with different input formats, which could cause slight confusion, but their descriptions clearly differentiate them.
All tool names follow a consistent verb_noun_from_noun pattern (e.g., generate_image_from_text, transform_image_from_encoded, transform_image_from_file). This uniformity makes the set predictable and easy to understand, with no deviations in style or convention.
With only 3 tools, the server feels slightly thin for an image generation domain, as it lacks operations like listing, deleting, or managing generated images. However, the count is reasonable for basic functionality, covering core tasks without being excessive.
The tools cover generation and transformation of images, which are key operations, but there are notable gaps. For example, there is no way to retrieve, update, or delete generated images, and no tools for batch processing or status checking, which could limit agent workflows in a full image management context.