kinoscripter
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KINOSCRIPTER_DIR | No | The folder containing your .kinoscript.json files (created if missing). Can also be passed as a positional argument instead of this environment variable, e.g. `node server.mjs ~/Kinoscripts`. |
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": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_scriptsA | List the Kinoscripter scripts in the folder with their size (acts, scenes, beats). |
| read_scriptA | Read a script. format "text" (default) is the whole script with act/scene/beat ids to quote in edits; "outline" is the same as JSON; "json" is the raw editor document. |
| create_scriptA | Create a new script file (one act, one scene, one empty beat). Never overwrites. |
| insert_beatA | Add a beat (one moment: what we see beside what we hear). Goes after afterBeatId, else at the end of sceneId, else at the end of the script. Plain text; one line per paragraph. A little markdown is kept: "# " headings, "- " bullets, "> " quotes, bold, italic. |
| edit_beatC | Replace the video and/or audio of a beat. Plain text; one line per paragraph. A little markdown is kept: "# " headings, "- " bullets, "> " quotes, bold, italic. |
| insert_sceneB | Add a scene (with one beat) after afterSceneId, else at the end of act N (1-based), else at the end. |
| insert_actA | Add an act (with one scene and one beat) at the end, or after act N (1-based). |
| validate_scriptA | Check a script file against the editor's structure rules. Lists every problem with its path. |
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 8 tools
Each tool has a clearly distinct purpose: listing/reading/creating scripts, inserting beats/scenes/acts, editing beats, and validating structure. The insert versus edit distinction is clear, and hierarchical inserts are separated by structural level.
All tool names follow a consistent snake_case verb_noun pattern: list_scripts, read_script, create_script, insert_beat, edit_beat, insert_scene, insert_act, validate_script. There are no mixed conventions or vague standalone verbs.
Eight tools is well-scoped for a script-editing server with acts, scenes, and beats. Each tool maps to a meaningful operation without obvious redundancy or unnecessary surface area.
The core workflow of creating, reading, inserting, editing beats, and validating is covered, but there are no delete/remove operations for scripts, acts, scenes, or beats. Scene/act editing and reordering/moving are also absent, leaving notable lifecycle gaps.