klaket-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KLAKET_API_URL | No | The URL of the Klaket API server | http://localhost:8484 |
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 |
|---|---|
| klaket_ingestA | Start processing a video (URL or server-side file path) into LLM-ready data. Returns a job id — poll klaket_job_status until status is 'done', then call klaket_get_result. |
| klaket_job_statusA | Check the status of a Klaket ingest job (queued | processing | done | failed). |
| klaket_get_resultA | Get the processed video as LLM-ready markdown: timestamped transcript, scene list with descriptions and on-screen text. Only works when the job status is 'done'. |
| klaket_find_momentA | Search inside a processed video: finds the moments (timestamped transcript lines, on-screen text or scene descriptions) matching a query. Job must be 'done'. |
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 distinct purpose: ingest starts processing, job_status checks progress, get_result retrieves markdown, and find_moment searches within processed video. There is no functional overlap.
All tools use the 'klaket_' prefix and snake_case, with three following a verb_noun pattern (ingest, get_result, find_moment) and one being noun_noun (job_status). The pattern is mostly consistent but has a minor deviation.
With 4 tools, the server is well-scoped for its purpose of video ingestion and querying. Each tool serves a necessary step in the workflow without unnecessary bloat.
The tool set covers the core lifecycle (ingest, status, retrieve, search) but lacks deletion or listing capabilities. This is acceptable for a focused server, though minor gaps exist.