kairouter-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KAIROUTER_API_KEY | Yes | Your KaiRouter API key, required for video generation and job management tools. Not needed for list_video_models. | |
| KAIROUTER_API_URL | No | Override to point to a staging/local KaiRouter instance. | https://kairouter.com |
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 |
|---|---|
| list_video_modelsA | List the video generation models currently active on KaiRouter (BytePlus Seedance family and others), with id, pricing, and live provider health. Call this first to find a valid model id for generate_video — model availability changes over time, so don't assume a model id without checking here. |
| generate_videoA | Start an async video generation job on KaiRouter (e.g. BytePlus Seedance 2.0 / 2.0 Fast / 2.0 Mini / 1.5 Pro / 1.0 Pro — see list_video_models for the exact ids currently available). Returns immediately with a job id and status 'queued'; it does NOT wait for the video to finish. Call check_video_status with the returned id to poll until status is 'succeeded' (or 'failed'). Deducts real credits from the caller's KaiRouter account balance when the job is accepted. |
| check_video_statusA | Poll the status of a video generation job started with generate_video. status is one of 'queued', 'processing', 'succeeded', 'failed'. Once status is 'succeeded', video_url has the finished video. Poll every few seconds — generation typically takes tens of seconds to a few minutes depending on model and resolution. |
| list_video_jobsA | List the caller's most recent video generation jobs (up to 50), most recent first. Useful for recovering a job id that was lost, or reviewing recent generations. |
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 has a clear, non-overlapping purpose: listing available models, listing past jobs, submitting a generation job, and polling its status. There is no ambiguity between them, and the descriptions reinforce distinct roles.
All tool names follow a consistent verb_noun pattern (list_video_models, list_video_jobs, generate_video, check_video_status). The naming is predictable and maintains the same style across the set.
With only 4 tools, the set is tightly scoped for its purpose—a video generation API router. Each tool is essential for the core workflow (discover models, generate, check status, review history) without unnecessary extras.
The toolset covers the primary lifecycle: listing models, creating a job, polling status, and retrieving past jobs. The only minor gap is the lack of cancellation or deletion options, but these are not critical for the core use case and can be worked around.