JsonCut
Start creating free
MCP FOR AGENTS

Let an agent create.
Keep the project reviewable.

Create short outputs directly or build longer work scene by scene with uploads, patches, checkpoints and visual review.

Try it in StudioBrowse examples
FOLD/READ — Document AI Loop — editable JsonCut video example
Editable Video · 1080 × 1080 · 1:1FOLD/READ — Document AI Loop
01Short + long workflows02Scene-level patches03Frame review
WHAT IT IS

JsonCut MCP exposes project-oriented authoring tools designed for iterative image and video creation.

SEE THE WORKFLOW

Short + long workflows
Scene-level patches

JsonCut MCP exposes project-oriented authoring tools designed for iterative image and video creation.

MCP FOR AGENTSfinish_small_work_without_ceremonybuild_longer_work_incrementallylook_before_final_rendering
Frame reviewAgent-created campaignsreview and patch
Frame review
THE CONNECTION

Finish small work without ceremony.
Look before final rendering.

01Finish small work without ceremonyShort + long workflows
02Build longer work incrementallyScene-level patches
03Look before final renderingFrame review
HOW IT WORKS IN STUDIO

Enough control for real work.
Only when you need it.

Create short outputs directly or build longer work scene by scene with uploads, patches, checkpoints and visual review.

01 · QUICK PATH

Finish small work without ceremony

Short image and video requests can use a concise creation path without mandatory scene planning.

02 · PROJECT PATH

Build longer work incrementally

Create a project, add scenes, patch only the relevant scope and keep each request small enough to inspect.

03 · UPLOADS

Work with real files

Temporary scoped upload URLs let an agent bring image, video and audio resources into the project.

04 · REVIEW

Look before final rendering

Single images and configurable multi-frame grids expose composition, pacing and scene continuity to the agent.

THE CAPABILITIES

What makes mcp for agents useful in real work.

Each capability remains connected to the same editable JsonCut project.

01

Take the shortest useful path

Simple outputs can be created directly without forcing every task through scenes.

02

Build long work incrementally

Projects, scene patches and checkpoints avoid oversized single requests for longer videos.

03

Inspect visual progress

Images and configurable frame grids let agents review composition and motion before export.

FROM FIRST DRAFT TO OUTPUT

Finish small work without ceremony.
Look before final rendering.

1

Finish small work without ceremony

Short image and video requests can use a concise creation path without mandatory scene planning.

2

Build longer work incrementally

Create a project, add scenes, patch only the relevant scope and keep each request small enough to inspect.

3

Look before final rendering

Single images and configurable multi-frame grids expose composition, pacing and scene continuity to the agent.

USE IT FOR

Agent-created campaigns.
And the work after it.

01Agent-created campaigns
02Long-form structured video
03Template discovery and fills
QUESTIONS

Know what the feature changes.

01Is this available in both image and video projects?

The page states where a capability applies. Shared controls use the same visual language in both editors.

02Does it remain editable after using AI?

Yes. The assistant changes ordinary project layers and versions, so you can inspect and refine the result.

03Can the same result be automated?

Yes. Projects can become typed templates or be rendered through the focused V2 API and MCP surface.

KEEP EXPLORING

Connect the capability to real work.

MCP productMCP setupAI Director
TRY IT IN THE REAL STUDIO

See the control.
Keep the result editable.

Start a free project and use the same feature in the image or video workflow it belongs to.

Start creating free