AI-video-generator-MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| create_videoA | Start generating a video from a text prompt. Returns immediately with a job_id; the video is not ready yet. Poll get_video_status with that job_id until the status is 'completed', then call get_video_result to retrieve the video. |
| get_video_statusA | Check the progress of a video-generation job. Use the job_id returned by create_video. Statuses are 'queued', 'running', 'completed' and 'cancelled'. Keep polling while the job is queued or running. |
| get_video_resultA | Retrieve the finished video for a completed job. Only works once get_video_status reports 'completed'. Calling it earlier is an error, not a wait. |
| cancel_videoA | Cancel a video-generation job that has not finished yet. Jobs that are already completed or cancelled cannot be cancelled. |
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 maps to a distinct stage of the asynchronous video-generation workflow: create starts a job, status polls progress, result retrieves output, and cancel aborts a pending job. No two tools overlap in purpose or return type.
All tool names use a consistent verb_noun snake_case pattern: create_video, get_video_status, get_video_result, and cancel_video. The get_ prefix is consistently used for retrieval operations, making the API surface easy to predict.
Four tools is an appropriate size for this narrow domain; each tool has a clear, necessary role in the async job lifecycle. There is no redundancy or obvious missing basic operation.
The set supports the full create, poll, retrieve, and cancel workflow for video generation. The main gap is that get_video_status does not expose a 'failed' terminal state, so error handling requires a workaround such as a client-side timeout.