Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_NAME | No | Name for the MCP server (optional) | gemini-2-5-flash-mcp |
| MCP_HTTP_PATH | No | Path for HTTP transport mode | /mcp |
| MCP_HTTP_PORT | No | Port for HTTP transport mode | 7801 |
| MCP_TRANSPORT | No | Transport mode for MCP (http for HTTP mode, otherwise STDIO) | |
| GEMINI_API_KEY | Yes | Google Gemini API key (required) | |
| MCP_HTTP_ENABLE_JSON | No | Enable JSON responses instead of SSE streaming for HTTP mode | false |
| GEMINI_IMAGE_ENDPOINT | No | Gemini image generation endpoint URL (optional) | https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-image-preview:generateContent |
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_image | Generate an image from a text prompt using Gemini 2.5 Flash Image |
| edit_image | Edit an image using a prompt. Provide one input image via base64 or file path. |
| compose_images | Compose a new image using multiple input images and a guiding prompt. |
| style_transfer | Transfer style from a style image to a base image, guided by an optional prompt. |