Budka MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BUDKA_API_KEY | Yes | Your API key for Budka MCP (CyberPhotoBooth 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 |
|---|---|
| get_modelsA | Returns the list of available image generation models. Use this when user asks which models are available. |
| get_aspect_ratiosA | Returns the list of available aspect ratios for image generation. Pass a mode to get ratios for a specific model, or omit to see all ratios grouped by model. |
| create_promptA | Generates an optimized English prompt for Flux Klein image generation model based on your description. Describe what you want (theme, style, mood) and get back a well-structured prompt following best practices. The prompt will be universal (no gender/count specifics). |
| check_jobA | Check the status of a previously submitted image generation job. Use this if generate_image timed out or was interrupted, to retrieve the result without creating a new job. |
| generate_imageA | Generates an image using the Budka (CyberPhotoBooth) API. Async: submits a job then polls for result. Statuses: queued → processing → completed/failed. If timed out or interrupted, use check_job with the job_id to retrieve the result without creating a new job. Requires BUDKA_API_KEY. |
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 5 tools
Each tool has a distinct purpose: models, aspect ratios, prompt generation, job creation, and job status checking. Even get_models and get_aspect_ratios are clearly separated by resource type, and generate_image vs check_job are unambiguously create vs retrieve.
All tools follow a consistent verb_noun pattern in snake_case: get_models, get_aspect_ratios, create_prompt, check_job, generate_image. The verbs and nouns clearly indicate the action and target, making the API predictable.
Five tools is well-scoped for an image generation server, covering configuration, prompt creation, generation, and status retrieval without unnecessary bloat or missing essentials.
The core image generation lifecycle is covered: list models, list ratios, create prompt, submit job, check job. Minor gaps like a cancel or list-jobs tool are absent, but agents can work around them since check_job relies on a job_id from generate_image.