jianying-editor
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| jianying_open_draftA | Open an existing JianYing draft by name and return its timeline structure, so work can be resumed. Use this to inspect or continue a draft listed by jianying_list_drafts. Pass overwrite only to deliberately discard the existing draft and start over. |
| jianying_create_draftA | Create a new JianYing draft and return its structure. Set width/height to match the source footage (1080x1920 for 9:16 vertical, 1920x1080 for 16:9). When omitted, the canvas adopts the first video's resolution automatically. |
| jianying_close_draftA | Close an open draft and release its memory. Unsaved changes are lost, so call jianying_save_draft first. Use this when a draft is finished or was created by mistake. |
| jianying_list_draftsA | List all JianYing drafts found under the drafts root, with duration and canvas size. Use this before opening an unknown draft. |
| jianying_add_videoA | Add a video or image clip to a video track. When 'start' is omitted the clip is appended after the current track content. |
| jianying_add_audioB | Add an audio clip (BGM, voiceover, sound effect) to an audio track. Use track 0 for the main audio bed and track 1 for narration. |
| jianying_add_textB | Add a text or subtitle segment to the text track. Use for titles, lower thirds and single captions. |
| jianying_add_subtitlesA | Add a full subtitle track from a script. The script is split into short lines (Chinese ads use ~18 chars/line) and distributed evenly across the time window. Returns the generated lines so they can be proofread. |
| jianying_remove_mediaB | Remove every clip that references the given media file from the timeline. |
| jianying_save_draftA | Write the current timeline to disk as a JianYing draft. Call this last — the draft only becomes visible to JianYing after saving. |
| jianying_inspect_draftA | Return the structured timeline of the open draft: tracks, segments, timing and materials. Use this as the acceptance check after editing. |
| jianying_export_srtB | Export the text track of the open draft as an SRT subtitle file, so the captions can be checked in any subtitle editor. |
| jianying_probe_mediaA | Probe a media file for duration, resolution and type. Use this before adding clips so durations can be planned. |
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 13 tools
Each tool targets a distinct phase of the draft workflow (list/open/create/save/close, add clip types, inspect, probe, remove media), and the descriptions clearly separate similar tools like add_text vs add_subtitles. The one soft overlap is jianying_open_draft, which both opens a draft and returns its timeline structure, versus jianying_inspect_draft, which returns the same structure for an already-open draft.
Every tool follows the same jianying_<verb>_<noun> snake_case pattern (open_draft, add_video, export_srt, probe_media), with no camelCase or verb-style deviations. The uniform prefix also makes the whole surface easy to recognize as one cohesive family.
Thirteen tools is well within a comfortable range for a domain-specific editor integration, and each tool maps to a concrete editing operation. Nothing looks redundant or padded at the count level.
The draft lifecycle (list/create/open/save/close/inspect) and content insertion (video, audio, text, subtitles) plus SRT export are covered, but segment-level editing is missing: there is no way to move, trim, or delete an individual clip except via jianying_remove_media, and no tool to delete a draft. These gaps will force agents into dead ends for common revision tasks.