gpt-image-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HOST | No | HTTP listen host. CLI flag --host takes precedence. | 127.0.0.1 |
| MCP_PATH | No | MCP endpoint path. CLI flag --path takes precedence. | /mcp |
| MCP_PORT | No | HTTP listen port. CLI flag --port takes precedence. | 3000 |
| ALLOWED_HOSTS | No | Cloudflare Worker runtime comma-separated allowed Host hostnames. Empty disables the check. | |
| MCP_TRANSPORT | No | Transport method (stdio or http). CLI flag --transport takes precedence. | stdio |
| ALLOWED_ORIGINS | No | Cloudflare Worker runtime comma-separated allowed Origin hostnames. Empty disables the check. | |
| MCP_ALLOWED_HOSTS | No | Comma-separated allowed Host hostnames for the Node HTTP server. | |
| MCP_ALLOWED_ORIGINS | No | Comma-separated allowed Origin hostnames for the Node HTTP server. |
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_imageC | 通过 OpenAI Images API(/v1/images/generations)生成图片,支持 gpt-image-2 与 gpt-image-2.5 系列模型。 |
| edit_imageA | 通过 OpenAI Images API(/v1/images/edits)编辑图片,支持单图、多图、mask 与 gpt-image-2 / 2.5 系列模型。 |
| generate_image_via_responsesA | 通过 OpenAI Responses API 的 image_generation 工具生成图片,支持 previous_response_id 多轮编辑与参考图输入。 |
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
generate_image and generate_image_via_responses both create images, so there is potential overlap, but the descriptions clearly distinguish the underlying API and the multi-turn/reference-image capability. edit_image is clearly separate. An agent can choose correctly if it reads descriptions, though the generation split could still cause minor hesitation.
All tool names follow a verb_noun pattern and are consistently snake_case. generate_image_via_responses adds a longer qualifier but remains readable and intentional. Minor deviation only.
Three tools are well-scoped for an image generation/editing server: generate via one API, generate via another API with multi-turn support, and edit. Each tool earns its place without unnecessary surface area.
The core image lifecycle is covered: generation and editing, including masks, multiple images, references, and multi-turn editing. Some optional operations like variations or upscaling are absent, but the primary workflows are present.