Clip Studio MCP

generate_video_lab

Start a paid Video Lab generation. Uses this month’s generation allowance. Poll get_video_lab_generation until it finishes. FLUX 3 Edit clip uses mode=edit_video plus the same source clip used on the quote. Duration and aspect follow the source; output is 720p. Keeps the source clip’s audio.

Input Schema

TableJSON Schema

Name	Required	Description
`fps`	No	Frames per second when the catalog lists that control.
`mode`	No	Input mode: text_to_video, image_to_video, first_last_frame, reference_to_video, or edit_video. Must match the quote when quoteId is set.
`seed`	No	Seed when the catalog lists that control.
`style`	No	Style id when the catalog lists that control. Omit or none for the default look.
`prompt`	No	What to film. Omit when quoteId is set. Up to 8,192 UTF-8 bytes when quoting from generate.
`quoteId`	No	Quote id from quote_video_lab. Optional; generate quotes first when omitted if modelSlug and prompt are set.
`inputMode`	No	Same as mode: text_to_video, image_to_video, first_last_frame, reference_to_video, or edit_video.
`modelSlug`	No	Video Lab model slug from list_video_lab_models. Required unless quoteId is set.
`multiShot`	No	Multi-shot / intelligent shot type when the catalog lists that control.
`resolution`	No	Output resolution from the model catalog. Omit when quoteId is set.
`aspectRatio`	No	Frame size from the model catalog. Omit when quoteId is set.
`audioEnabled`	No	Native audio flag for models that list audio as optional. Omit when quoteId is set.
`sourceClipId`	No	Library clip id used as the edit_video source. Prefer passing the quote’s source video asset id on generate.
`klingElements`	No	Kling 3 Pro / Kling 3 4K subject packs. Each element needs a frontal still and supporting references. The first primary still is the start frame when startImageAssetId is omitted. Do not send leftover stills as sourceAssetIds references on those models.
`idempotencyKey`	No	UUID to retry an ambiguous submit. Not a Video Lab batch key. Reuse the same key and inputs; the service mints a single-clip batch after the quote is accepted.
`negativePrompt`	No	Negative prompt when list_video_lab_models lists that control for the mode.
`sourceAssetIds`	No	Same source generation-asset ids used on the quote.
`sourceVideoUrl`	No	Public MP4 URL used as the edit_video source. Prefer passing the quote’s source video asset id on generate.
`durationSeconds`	No	Clip length in seconds. Omit when quoteId is set; generate uses the quoted setup.
`endImageAssetId`	No	End-frame generation-asset id. Same as sourceAssetIds[1] for first_last_frame.
`promptEnhancement`	No	Prompt expansion when the catalog lists that control. false maps to fal disabled on MiniMax H3 and H3 Max.
`startImageAssetId`	No	Start-frame generation-asset id. Same as sourceAssetIds[0] for image_to_video and first_last_frame.
`sourceVideoAssetId`	No	Source MP4 generation-asset id for edit_video. Same as sourceAssetIds[0] for that mode.
`referenceImageAssetIds`	No	Reference stills for reference_to_video. Do not send leftover stills here on Kling 3 Pro / Kling 3 4K when klingElements is set.

Output Schema

TableJSON Schema

Name	Required	Description
`status`	No	Job status such as pending, queued, in_progress, completed, or failed.
`videoId`	No	Library clip id for this job, when one exists.
`idempotent`	No	True when this call reused an in-flight or finished job with the same idempotency key.
`generationId`	Yes	Generation id. Poll the matching get_* tool until status is completed or failed.
`creditsCharged`	No	Usage already consumed from this month’s generation allowance (internal units).

Schema Changelog

Changes observed during successful MCP inspections.

Changed18 schema fields changedSep 27, 2026

changedInput schema / properties / aspectRatio / description

Previous value: -"Frame size from the model catalog. Must match the quote when quoteId is set."New value: +"Frame size from the model catalog. Omit when quoteId is set."

changedInput schema / properties / audioEnabled / description

Previous value: -"Native audio flag for models that list audio as optional. Must match the quote when quoteId is set."New value: +"Native audio flag for models that list audio as optional. Omit when quoteId is set."

changedInput schema / properties / durationSeconds / description

Previous value: -"Clip length in seconds. Must match the quote when quoteId is set."New value: +"Clip length in seconds. Omit when quoteId is set; generate uses the quoted setup."

addedInput schema / properties / endImageAssetId

Added value: +{
+  "description": "End-frame generation-asset id. Same as sourceAssetIds[1] for first_last_frame.",
+  "type": "string"
+}

addedInput schema / properties / fps

Added value: +{
+  "description": "Frames per second when the catalog lists that control.",
+  "type": "number"
+}

addedInput schema / properties / inputMode

Added value: +{
+  "description": "Same as mode: text_to_video, image_to_video, first_last_frame, reference_to_video, or edit_video.",
+  "type": "string"
+}

addedInput schema / properties / klingElements

Added value: +{
+  "description": "Kling 3 Pro / Kling 3 4K subject packs. Each element needs a frontal still and supporting references. The first primary still is the start frame when startImageAssetId is omitted. Do not send leftover stills as sourceAssetIds references on those models.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "primaryImageAssetId": {
+        "description": "Frontal still generation-asset id from complete_generation_asset.",
+        "type": "string"
+      },
+      "referenceImageAssetIds": {
+        "description": "Supporting stills for this Kling subject.",
+        "items": {
+          "description": "Supporting still generation-asset id.",
+          "type": "string"
+        },
+        "type": "array"
+      }
+    },
+    "required": [
+      "primaryImageAssetId"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedInput schema / properties / multiShot

Added value: +{
+  "description": "Multi-shot / intelligent shot type when the catalog lists that control.",
+  "type": "boolean"
+}

addedInput schema / properties / negativePrompt

Added value: +{
+  "description": "Negative prompt when list_video_lab_models lists that control for the mode.",
+  "type": "string"
+}

changedInput schema / properties / prompt / description

Previous value: -"What to film. Up to 8,192 UTF-8 bytes. Must match the quoted setup when quoteId is set."New value: +"What to film. Omit when quoteId is set. Up to 8,192 UTF-8 bytes when quoting from generate."

addedInput schema / properties / promptEnhancement

Added value: +{
+  "description": "Prompt expansion when the catalog lists that control. false maps to fal disabled on MiniMax H3 and H3 Max.",
+  "type": "boolean"
+}

addedInput schema / properties / referenceImageAssetIds

Added value: +{
+  "description": "Reference stills for reference_to_video. Do not send leftover stills here on Kling 3 Pro / Kling 3 4K when klingElements is set.",
+  "items": {
+    "description": "Reference still generation-asset id.",
+    "type": "string"
+  },
+  "type": "array"
+}

changedInput schema / properties / resolution / description

Previous value: -"Output resolution from the model catalog. Must match the quote when quoteId is set."New value: +"Output resolution from the model catalog. Omit when quoteId is set."

addedInput schema / properties / seed

Added value: +{
+  "description": "Seed when the catalog lists that control.",
+  "type": "number"
+}

addedInput schema / properties / sourceVideoAssetId

Added value: +{
+  "description": "Source MP4 generation-asset id for edit_video. Same as sourceAssetIds[0] for that mode.",
+  "type": "string"
+}

addedInput schema / properties / startImageAssetId

Added value: +{
+  "description": "Start-frame generation-asset id. Same as sourceAssetIds[0] for image_to_video and first_last_frame.",
+  "type": "string"
+}

addedInput schema / properties / style

Added value: +{
+  "description": "Style id when the catalog lists that control. Omit or none for the default look.",
+  "type": "string"
+}

removedInput schema / required
```
Removed value: -[
-  "prompt"
-]
```

First observedSep 20, 2026

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations establish this as a non-read-only, non-destructive, closed-world write, so the description's job is to add cost and lifecycle context. It does: "paid" plus "uses this month's generation allowance" signals consumption/irreversibility, and the polling directive discloses the async nature. It does not discuss idempotency/retry behavior, which is left to the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four tightly packed sentences with no filler: purpose, cost, lifecycle, then the one mode-specific caveat. The most decision-relevant facts (paid, poll, mode constraint) are front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need not be explained, and the schema covers all 24 optional parameters. The description supplies the cost, async, and mode caveats an agent needs, though the quote-first prerequisite and the meaning of the zero-required-parameter surface are largely delegated to the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the parameter baseline is 3. The description goes beyond the schema by stating the edit_video constraint (use mode=edit_video plus the same source clip used on the quote, duration/aspect follow source, 720p output, source audio retained) — genuine semantic context that constrains how sourceClipId, mode, durationSeconds, and aspectRatio must be supplied.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence gives a precise verb and resource ("Start a paid Video Lab generation") and the word "paid" plus the allowance note distinguishes it from the free quote_video_lab step. The FLUX 3 Edit sentence further scopes one mode. An agent can tell this apart from quote_video_lab, get_video_lab_generation, and list_video_lab_models without opening schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Poll get_video_lab_generation until it finishes" gives the required follow-up action after invocation, and the edit_video note tells the agent when a special input path applies. It stops short of an explicit "call quote_video_lab first when quoteId is absent" instruction in the description (that lives only in the schema), so the when-to-use routing is clear but not fully closed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Clip Studio MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?