kinocut
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.
Kinocut is a video editing MCP server. Default path: inspect (info/doctor) → plan (video_intent or cutfile) → render → quality check → human review. Do not publish without QC and a human gate. Prefer video_intent verbs over listing every tool. The default surface reaches every operation through the typed family tools (video_edit_ops, video_plan_ops, ...): pick the operation with list_operations, pass its exact arguments in params. Paths should be absolute. Output is auto-generated if omitted. Paths are on the machine running this server: if your shell cannot see an output, the server runs in a container or on another host, so inspect it with Kinocut tools instead of re-running the job locally.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| video_infoA | Probe a video file for metadata. Returns JSON {success, info:{duration, resolution, codec, fps, size, ...}}. Use before any edit to learn the source's dimensions and length. |
| video_trimB | Cut a segment out of a video by start time and duration or end. Returns JSON {success, output_path} pointing at the rendered clip. |
| video_mergeB | Concatenate two or more video clips, in order, into one rendered file. Returns JSON {success, output_path}. |
| video_add_textB | Burn one text element (title, caption, watermark) into a video. Returns JSON {success, output_path}. |
| video_add_audioA | Add, replace, or mix an audio track into a video and render a new file; the sources are only read. Returns JSON {success, output_path}. |
| video_doctorA | Return a read-only JSON readiness verdict for the next video job. |
| video_extract_frameA | Extract one frame as an image. Without a timestamp, picks a smart thumbnail (fallback: 10% into the clip); pass 0 for the first frame. |
| video_shortsB | Trim, caption, make vertical, and export selected segments in one call. |
| list_operationsA | List operations: families with member counts, and each operation's family, verb, required parameters and side-effect annotations. |
| describe_operationA | Return one operation's full inputSchema, the family tool that dispatches it, and its kino CLI route when one exists. |
| video_edit_opsC | Run one edit operation by name; params holds its arguments. Required arguments: list_operations; full schema: describe_operation. |
| video_effects_opsA | Run one effect operation by name; params holds its arguments. Required arguments: list_operations; full schema: describe_operation. |
| audio_opsB | Run one audio operation by name; params holds its arguments. Required arguments: list_operations; full schema: describe_operation. |
| video_ai_opsA | Run one AI operation by name; params holds its arguments. Required arguments: list_operations; full schema: describe_operation. |
| image_opsB | Run one image/still operation by name; params holds its arguments. Required arguments: list_operations; full schema: describe_operation. |
| video_qc_opsB | Run one inspection/release operation by name; params holds its arguments. Required arguments: list_operations; full schema: describe_operation. |
| video_plan_opsC | Run one planning operation by name; params holds its arguments. Required arguments: list_operations; full schema: describe_operation. |
| platform_opsB | Run one platform operation by name; params holds its arguments. Required arguments: list_operations; full schema: describe_operation. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| templates_resource | List available editing templates (aspect ratios, quality presets). |
TDQS
Scored across 18 tools
Eight dispatcher tools (video_edit_ops, video_effects_ops, video_qc_ops, video_plan_ops, video_ai_ops, audio_ops, image_ops, platform_ops) share essentially identical descriptions and signatures, differing only by family name, so the agent must guess which family holds the operation it needs. There is also overlap between direct tools (video_trim, video_merge, video_add_text, video_add_audio) and the edit/effects/audio dispatchers, which plausibly contain the same operations.
Most names use snake_case with a video_ prefix, but the set mixes two conventions: concrete verb_noun tools (video_add_text, video_trim, video_extract_frame) and generic family dispatchers ending in _ops. The two meta-tools list_operations and describe_operation drop the prefix entirely, adding a third minor deviation.
At 18 tools this sits in the borderline-heavy band, and the count is inflated by eight near-duplicate dispatchers that provide little surface-level differentiation. The dispatcher pattern does cap growth as operations expand, so the total is defensible but not tight.
The surface covers the core video lifecycle — probe, trim, merge, text, audio, frame extraction, shorts assembly, readiness check — plus dispatchers for edit, effects, QC, planning, AI, image and platform operations. Coverage is broad; the main weakness is that most capability is hidden behind an undisclosed operation catalog rather than directly discoverable tools.