Gemini Image Gen MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GCP_REGION | No | GCP region for Vertex AI. | us-central1 |
| GEMINI_MODEL | No | Default model to use. Can be overridden per request. | gemini-2.0-flash-exp-image-generation |
| GCP_PROJECT_ID | No | GCP project ID (required only for Vertex AI). | |
| GEMINI_API_KEY | No | API key for AI Studio or GCP API key for Vertex AI. Not required if using Application Default Credentials (ADC) with Vertex AI. | |
| GEMINI_PROVIDER | No | Provider to use: 'ai-studio' (default) or 'vertex-ai'. | ai-studio |
| IMAGE_OUTPUT_DIR | No | Directory to save generated images. | ./output |
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": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_imageA | Generate an image from a text prompt using Google Gemini or Imagen. Provider: ai-studio. Default model: gemini-3.1-flash-image. Available models: |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Model Selection Guide | Available models, pricing, quality comparison, and selection tips |
| Provider Configuration Guide | How to configure AI Studio and Vertex AI providers |
TDQS
Scored across 1 tool
Only one tool exists, so there is zero ambiguity in tool selection. The agent can only choose this single tool.
With a single tool, naming consistency is trivially maintained. The verb_noun pattern 'generate_image' is clear and follows convention.
One tool is on the low end of what's reasonable for a server. While the server has a narrow purpose (image generation), it may be too restrictive for agents needing additional capabilities like model listing or image variation.
The tool fully covers the server's stated purpose of generating an image from a text prompt. No obvious missing functionality within the declared scope.