kling-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RUNAPI_API_KEY | No | Your RunAPI API key. If not set, the server will look for the key in ~/.config/runapi/config.json. |
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
} |
| logging | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| loginA | Authenticate RunAPI by opening a browser PKCE login flow and saving the API key to ~/.config/runapi/config.json. |
| ai_avatarC | Create a Kling task on RunAPI (ai avatar). Returns a task id, status, and output URLs. |
| edit_videoC | Create a Kling task on RunAPI (edit video). Returns a task id, status, and output URLs. |
| extend_videoC | Create a Kling task on RunAPI (extend video). Returns a task id, status, and output URLs. |
| image_to_videoB | Create a Kling task on RunAPI (image to video). Returns a task id, status, and output URLs. |
| motion_controlC | Create a Kling task on RunAPI (motion control). Returns a task id, status, and output URLs. |
| text_to_videoC | Create a Kling task on RunAPI (text to video). Returns a task id, status, and output URLs. |
| get_taskA | Fetch the current status and latest result payload for a kling task. |
| check_pricingC | Look up RunAPI pricing for the kling model line. |
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
The six task-creation tools map to distinct Kling video modes (text-to-video, image-to-video, extend, edit, motion control, AI avatar), so purposes are mostly clear. Minor potential confusion between extend_video and edit_video, but descriptions and names differentiate them adequately.
All names use snake_case consistently with no style mixing. However, the pattern is not uniformly verb_noun: some are source-to-target phrases (image_to_video), some are noun phrases (motion_control, ai_avatar), and others are verb_noun (get_task, check_pricing).
Nine tools is well-scoped for a video-generation API client. Each tool earns its place: six generation modes, one task-status fetcher, one pricing lookup, and one authentication helper.
Core workflows are covered: login, pricing check, task creation across modes, and task status retrieval. Minor gaps include no task cancellation, no task listing, and no direct video download (though output URLs are returned).