image-gen-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | No | Enables the Gemini provider | |
| OPENAI_API_KEY | No | Enables the OpenAI provider | |
| IMAGE_GEN_MCP_LOG_FILE | No | JSONL ledger path. Absolute path to relocate, `none` to disable the file | ~/.image-gen-mcp/images.jsonl |
| IMAGE_GEN_MCP_OUTPUT_DIR | No | Fallback output directory when a call passes no `output_path` | |
| IMAGE_GEN_MCP_TIMEOUT_MS | No | Per-request timeout to the provider API | 180000 |
| IMAGE_GEN_MCP_ALLOWED_DIRS | No | Comma separated directories that all reads and writes are confined to. See Security | |
| IMAGE_GEN_MCP_GEMINI_MODEL | No | Default Gemini model | gemini-3.1-flash-image |
| IMAGE_GEN_MCP_OPENAI_MODEL | No | Default OpenAI model | gpt-image-2 |
| IMAGE_GEN_MCP_DEFAULT_PROVIDER | No | `gemini` or `openai`. When unset: gemini if its key is set, else openai | key-based |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_imageA | Generate one or more images from a text prompt using Gemini or OpenAI image models and save them to disk. Returns the absolute saved file path(s) plus provider/model metadata. Strongly prefer passing an absolute output_path inside the current project so the file lands where you can use it. Each image costs real API credits. |
| edit_imageA | Edit or combine existing image file(s) using a text instruction: modify elements, restyle, add or remove content, or merge references. Reads the source image(s) from disk, saves the result as a NEW file (never overwrites sources), and returns the absolute saved path(s). |
| list_capabilitiesA | Report which image providers (gemini, openai) are configured in this server, the default provider and models, known model options, the output directory fallback, and any directory restriction in force. Call this first if unsure what is available or why a call failed. |
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 targets a distinct operation: generate creates new images from text, edit modifies existing images, and list_capabilities reports configuration. There is no overlap or ambiguity between them.
All tool names follow a clear verb_noun pattern: generate_image, edit_image, list_capabilities. This is consistent and predictable.
With 3 tools, the server is well-scoped for its purpose. Each tool covers a necessary function without unnecessary bloat, fitting the typical 3-15 tool range.
The server covers the core lifecycle for image generation and editing, plus a capabilities introspection tool. Minor gaps like listing or deleting generated images are not essential to its stated purpose.