codex-image-gen++
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CODEX_IMAGE_GEN_CONFIG | No | Optional environment override: absolute path to the configuration file (recommended). | |
| CODEX_IMAGE_GEN_API_KEY | No | Optional environment override: API key for the provider. | |
| CODEX_IMAGE_GEN_BASE_URL | No | Optional environment override: base URL for the OpenAI-compatible Images API. |
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 |
|---|---|
| list_modelsA | List models visible to the configured provider API key. Does not generate images or prove generation permission. image_candidate is only a name heuristic. |
| generate_imageA | Submit one paid image-generation request and save bytes locally. Returns paths/metadata or a job ID to poll with get_job. Never automatically resubmit after timeout/failure. Existing files are protected. |
| edit_imageA | Edit local images using the provider multipart Images Edits API. Saves to a new absolute path; preserves originals. Optional mask follows provider semantics. Poll returned job ID with get_job. |
| get_jobA | Query an existing image job without submitting or retrying. Jobs survive MCP disconnects while the local worker is alive. On interrupted/unknown outcome, inspect output paths/provider logs before considering another paid request. |
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 4 tools
Each tool has a clearly distinct purpose: list_models (discovery), generate_image (create), edit_image (modify), and get_job (poll). The descriptions explicitly disambiguate similar-sounding operations, e.g. generate_image vs. get_job and the warning that list_models doesn't prove generation permission.
All four tools follow a consistent verb_noun snake_case pattern (list_models, generate_image, edit_image, get_job). No mixing of conventions or vague verbs.
Four tools is a tight, well-scoped set for an image generation/editing server, with each tool earning its place. It's slightly lean, as there's no cancel or list-jobs operation.
The core lifecycle is covered: discover models, generate, poll job status, and edit images. Minor gaps remain around job management (no cancel_job or list_jobs), but agents can work around them.