Krea MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KREA_API_KEY | Yes | Your Krea API key |
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 |
|---|---|
| generate_imageA | Generate an image using Krea AI. Returns a job_id - use get_job to check status and get the result URL. |
| generate_videoA | Generate a video using Krea AI. Returns a job_id - use get_job to check status and get the result URL. |
| get_jobA | Get the status and results of a generation job. Returns status (scheduled, processing, completed, failed) and result URLs when completed. |
| list_jobsC | List generation jobs with optional filtering |
| upload_assetA | Upload an image/video to Krea for use in generations |
| get_assetB | Get details of an uploaded asset |
| list_assetsC | List uploaded assets |
| search_stylesB | Search for styles/LoRAs to use in image generation |
| get_styleB | Get details of a specific style |
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 9 tools
Each tool targets a distinct operation: generation (image/video), asset management, job tracking, and style search. No ambiguity between tools.
All tool names follow a consistent verb_noun pattern using lowercase and underscores, e.g., generate_image, list_assets, search_styles.
9 tools cover the key operations for a generative AI service (generation, asset management, job tracking, style search) without redundancy.
Core operations are present: create (generate), read (get, list), and upload. Missing delete/update for assets or jobs, but these are minor gaps given the server's generative focus.