Image Forge
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| IMAGE_OUT_DIR | No | Output folder for generated images, created if missing. | ~/Downloads |
| IMAGE_FORGE_HISTORY | No | Generation log file path. | ~/.image-forge/history.jsonl |
| CLOUDFLARE_API_TOKEN | Yes | Cloudflare API token with permission Account → Workers AI → Read. Required to generate. | |
| CLOUDFLARE_ACCOUNT_ID | Yes | Cloudflare account ID, found in the right sidebar of Workers & Pages in the Cloudflare dashboard. Required to generate. | |
| IMAGE_FORGE_TIMEOUT_MS | No | Per-request timeout in milliseconds. | 90000 |
| IMAGE_FORGE_HARD_NEURONS | No | Hard stop before the daily Neurons limit. | 9500 |
| IMAGE_FORGE_MAX_INPUT_MB | No | Maximum input image size in MB. | 10 |
| IMAGE_FORGE_WARN_NEURONS | No | Warning threshold for estimated daily Neurons usage. | 8000 |
| IMAGE_FORGE_DEFAULT_MODEL | No | Model used when a call omits one. | flux-2-klein-4b |
| IMAGE_FORGE_MAX_IMAGES_PER_CALL | No | Cap on the count parameter. | 4 |
| IMAGE_FORGE_MULTIPART_IMAGE_FIELD | No | Multipart field name for FLUX.2 image input. | input_image |
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 |
|---|---|
| edit_imageA | Genera una nueva imagen a partir de otra imagen + un prompt. Guarda el resultado en disco y devuelve la ruta. |
| generate_imageA | Genera una imagen desde texto. Guarda el resultado en disco y devuelve la ruta. |
| get_image_infoA | Lee dimensiones, formato y tamaño de un archivo de imagen local. No consume API ni cuota. |
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 clearly distinct operation: text-to-image (generate_image), image+prompt-to-image (edit_image), and local metadata inspection (get_image_info). There is no plausible overlap; the descriptions explicitly contrast the source of input (text vs. existing image) and note that get_image_info consumes no API quota, further separating it.
All three names follow a strict verb_noun snake_case pattern (edit_image, generate_image, get_image_info), with verbs that accurately match the action. No camelCase mixing or vague verbs.
Three tools is a small but coherent surface for an image generation server — one per core action (generate, edit, inspect). It is slightly thin (no listing, batch, or transform operations), but nothing feels redundant or unearned.
The generate/edit/inspect cycle covers the primary workflow, but common adjacent operations are absent: resize/crop/convert, upscaling or variations, inpainting with masks, and any way to list or clean up previously written files. An agent can produce and inspect images but hits dead ends for post-processing or asset management.