Image Generation MCP Server

Please install the `image-generation-mcp` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install image-generation-mcp** — Install from PyPI (use [all] for OpenAI support) Run: `pip install image-generation-mcp[all]`

Canonical MCP server config (stdio transport):
- command: `image-generation-mcp`
- args: ["serve"]
- required environment variables:
  - `IMAGE_GENERATION_MCP_READ_ONLY`: Set to 'false' to enable write tools (generate_image). Defaults to 'true' (read-only). (example: `false`)
- optional environment variables:
  - `IMAGE_GENERATION_MCP_OPENAI_API_KEY`: OpenAI API key — enables OpenAI provider (example: `<your-openai-api-key>`)
  - `IMAGE_GENERATION_MCP_SD_WEBUI_HOST`: Stable Diffusion WebUI base URL — enables SD WebUI provider (example: `<your-sd-webui-host>`)
  - `IMAGE_GENERATION_MCP_SCRATCH_DIR`: Directory for saved generated images (example: `~/.image-generation-mcp/images/`)
  - `IMAGE_GENERATION_MCP_DEFAULT_PROVIDER`: Default provider (auto|openai|sd_webui|placeholder) (example: `auto`)
  - `IMAGE_GENERATION_MCP_BEARER_TOKEN`: Static bearer token for HTTP transport auth

Note: Multi-provider (OpenAI, SD WebUI, placeholder) image generation. READ_ONLY=true by default hides the generate_image tool; explicitly disable it. Also supports HTTP/SSE transport with bearer/OIDC auth.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.