Gemini Imagen 3.0 MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | Yes | Your Google Gemini API key |
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_imagesC | Generate images using Google Gemini AI |
| create_image_htmlB | Create HTML img tags from image file paths with gallery view |
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 2 tools
The two tools have completely distinct purposes: generate_images creates new images via AI, while create_image_html produces HTML img tags from existing file paths. There is no overlap or ambiguity between them.
Both tool names follow a verb_noun pattern (generate_images and create_image_html). The verbs 'generate' and 'create' are similar but not identical, and the nouns differ in structure (plural vs. compound), but the overall pattern is consistent and readable.
With only 2 tools, the server feels somewhat thin. While the scope is narrow (image generation and HTML formatting), this is borderline on the low end; a small utility set would benefit from at least one additional tool for managing or inspecting generated images.
The core workflow of generating images and then creating HTML for viewing is covered, but there are notable gaps: no way to list, delete, or manage previously generated images, and no tool to adjust model parameters beyond what might be embedded in generate_images. This limits the server to a single-generation flow.