image-gen-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OUTPUT_DIRECTORY | Yes | The output directory where generated images and artifacts are stored. | |
| AZURE_OPENAI_API_KEY | Yes | Your Azure Foundry API key for explicit API-key authentication. | |
| AZURE_OPENAI_ENDPOINT | Yes | The inference endpoint of your Azure Foundry deployment. | |
| AZURE_OPENAI_DEPLOYMENT | Yes | The deployment name for the configured model profile (gpt-image-2.5-sunburst). |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_capabilitiesC | Nonbillable configuration and capability diagnostics. Optional credential acquisition does NOT verify inference permission or deployment identity. |
| generate_imageA | Generate one billable Azure PNG at native 1536x864/high. Supply and retain a fresh UUID operation_id; replaying identical arguments recovers the same artifact without another submission. No retries, resizing or prompt rewrites. |
| edit_imageA | Create one new billable image from exactly one explicit source_artifact_id or approved absolute PNG source_path. Provide a self-contained prompt and new operation UUID. The source remains unchanged; masks, URLs and multiple references are unsupported. |
| get_operationA | Look up a retained operation UUID and recover a committed artifact after interruption. Never submits or resubmits an image request. Unknown completion may still incur charges. |
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 targets a clearly distinct operation: capabilities, generation, editing, and operation lookup. There is no meaningful overlap between generate_image and edit_image because the latter requires a source artifact.
All tool names use a consistent snake_case verb_noun pattern: get_capabilities, generate_image, edit_image, get_operation. The naming is predictable and easy to navigate.
Four tools is well-scoped for an image generation server. Each tool covers a necessary part of the workflow without unnecessary redundancy.
The core lifecycle is covered: generate, edit, and recover results via get_operation, plus capabilities discovery. Minor gaps like listing or deleting past operations exist, but they are not essential for the stated purpose.