kie
by tansilandre
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KIE_API_KEY | No | Your kie.ai API key (alternative name used by kie.ai docs). | |
| KIE_AI_API_KEY | No | Your kie.ai API key. KIE_API_KEY, the name kie.ai's own docs use, works too | |
| KIE_AI_DB_PATH | No | Where tasks and plans are stored (default ~/.kie-ai/tasks.db) | ~/.kie-ai/tasks.db |
| KIE_AI_CACHE_DIR | No | Where model schemas are cached (default ~/.kie-ai/cache, kept 24 hours) | ~/.kie-ai/cache |
| KIE_AI_CALLBACK_URL | No | Your own webhook for task completion | |
| KIE_AI_ENABLED_TOOLS | No | Comma-separated tool names to load, to keep the agent's context small | |
| KIE_AI_DISABLED_TOOLS | No | Tools to hide. Disabling a model tool such as veo3_generate_video does not stop the same model through run_model; disable run_model too | |
| KIE_AI_TOOL_CATEGORIES | No | Load whole categories: image, video, audio, catalog (run_model), utility | |
| KIE_AI_ALLOW_DIRECT_GENERATION | No | true lets every paid tool, including run_model with any catalog model, run without a plan. Leave it off | false |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues