@cloudinary/video-mcpv0.1.0
Stream live video, generate videos from images with AI, get timestamped visual transcripts of your videos, and build reusable video transformation pipelines.
Endpoints
| Endpoint | Method | Description |
|---|---|---|
| /mcp | POST | Streamable HTTP transportRecommended |
| /sse | GET | SSE transportDeprecated |
Server URL
https://staging-video.mcp.cloudinary.com/mcp
Configuration
Add this to your MCP client configuration. OAuth is used by default when no headers are provided.
{
"mcpServers": {
"@cloudinary/video-mcp": {
"url": "https://staging-video.mcp.cloudinary.com/mcp"
}
}
}
{
"mcpServers": {
"@cloudinary/video-mcp": {
"url": "https://staging-video.mcp.cloudinary.com/mcp",
"headers": {
"cloudinary-url": "cloudinary://api_key:api_secret@cloud_name"
}
}
}
}
Authentication
| Method | Description |
|---|---|
| OAuth 2.0 | Default. The OAuth flow is initiated automatically when the client connects with no auth headers. |
| API Key | Pass cloudinary-url header, or individual cloudinary-cloud-name, cloudinary-api-key, cloudinary-api-secret headers. |
Configuration Headers
Optional headers to customize server behavior. Applied at session creation time.
| Header | Description |
|---|---|
cloudinary-region |
API region: api, api-eu, or api-ap |
cloudinary-tools |
Comma-separated list of tools to enable (e.g. search-assets,list-images) |
Response Headers
API response headers are collected into _meta.headers on each tool result. The debug preset is active by default.
| Header | Description |
|---|---|
cloudinary-collect-headers |
Control which response headers are returned. Accepts:
debug — rate-limit + request ID (default)
ratelimit — rate-limit headers only
all — every response header
Or a comma-separated list of exact names, prefix:<value>, regex:<pattern>, and preset names
|
cloudinary-embed-headers |
Set to true to also include collected headers in the response body as _headers, for clients that don't surface _meta |
{
"_meta": {
"headers": {
"x-featureratelimit-limit": "5000",
"x-featureratelimit-remaining": "4998",
"x-featureratelimit-reset": "Thu, 13 Feb 2026 00:00:00 GMT",
"x-request-id": "bfeaccc60050594832508590a358a1a4"
}
},
"content": [{ "type": "text", "text": "{...}" }]
}
Available Tools (26)
List applets
Returns the account's saved Video Canvas applets as summaries, without their inputs, blocks, connections, or outputs.
| Parameter | Type | Description |
|---|---|---|
kind |
Abcstring | comma-separated applet kinds to return (derived, create); defaults to derived |
Create an applet
Creates an applet from its content (inputs, blocks, connections, and outputs). Cloudinary compiles the action blocks to validate them and returns the stored applet. For a derived applet, the compiled blocks are also saved as a named transformation.
| Parameter | Type | Description |
|---|---|---|
request required |
{ }object | The applet content to create. |
blocks required |
[ ]array | The nodes on the canvas. |
connections |
[ ]array | The directed edges between block ports. |
description |
Abcstring | An optional description of what the applet does. |
inputs |
[ ]array | The applet's declared parameters. |
kind |
Abcstring | Applet kind. Derived applets compile into a named transformation; create applets do not. Omit on update to keep the current kind. Switching to create leaves an existing named transformation as is; switching to derived creates or redefines it. |
name required |
Abcstring | A display name for the applet. |
outputs |
[ ]array | The applet's declared results. |
Get an applet
Returns a single applet with its full content, including its inputs, blocks, connections, and outputs.
| Parameter | Type | Description |
|---|---|---|
appletId required |
Abcstring | The server-generated id of the applet. |
Replace an applet's content
Replaces the full content of an existing applet and recompiles its action blocks to validate them. For a derived applet, its backing named transformation is also updated.
| Parameter | Type | Description |
|---|---|---|
appletId required |
Abcstring | The server-generated id of the applet. |
VideoCanvasAppletContentPayload required |
{ }object | The new applet content. |
blocks required |
[ ]array | The nodes on the canvas. |
connections |
[ ]array | The directed edges between block ports. |
description |
Abcstring | An optional description of what the applet does. |
inputs |
[ ]array | The applet's declared parameters. |
kind |
Abcstring | Applet kind. Derived applets compile into a named transformation; create applets do not. Omit on update to keep the current kind. Switching to create leaves an existing named transformation as is; switching to derived creates or redefines it. |
name required |
Abcstring | A display name for the applet. |
outputs |
[ ]array | The applet's declared results. |
Delete an applet
Deletes an applet and its stored content. For a derived applet, the named transformation that backs it isn't deleted, so delivery URLs and SDK calls that reference it keep working. To stop delivering the transformation, delete the named transformation separately.
| Parameter | Type | Description |
|---|---|---|
appletId required |
Abcstring | The server-generated id of the applet. |
Get a list of live streams
| Parameter | Type | Description |
|---|---|---|
request |
{ }object |
Create a new live stream
| Parameter | Type | Description |
|---|---|---|
request required |
{ }object | |
embedded_captions |
[ ]arraynull | |
idle_timeout_sec |
#integernull | |
input required |
{ }object | |
type required |
Abcstring | |
max_runtime_sec |
#integernull | |
name |
Abcstring |
Get a single live stream
| Parameter | Type | Description |
|---|---|---|
liveStreamId required |
Abcstring | live stream id |
Update a live stream
| Parameter | Type | Description |
|---|---|---|
liveStreamId required |
Abcstring | live stream id |
LiveStreamUpdatePayload required |
{ }object | |
embedded_captions |
[ ]arraynull | |
idle_timeout_sec |
#integernull | |
max_runtime_sec |
#integernull | |
name |
Abcstringnull |
Delete a live stream
| Parameter | Type | Description |
|---|---|---|
liveStreamId required |
Abcstring | live stream id |
Manually activate a live stream
| Parameter | Type | Description |
|---|---|---|
liveStreamId required |
Abcstring | live stream id |
Manually idle a live stream
| Parameter | Type | Description |
|---|---|---|
liveStreamId required |
Abcstring | live stream id |
Get a list of live stream outputs
| Parameter | Type | Description |
|---|---|---|
liveStreamId required |
Abcstring | live stream id |
Create a new live stream output
| Parameter | Type | Description |
|---|---|---|
liveStreamId required |
Abcstring | live stream id |
LiveStreamOutputCreatePayload required |
{ }object | |
asset_folder |
Abcstringnull | |
name |
Abcstringnull | |
public_id |
Abcstringnull | |
stream_key |
Abcstringnull | |
type required |
Abcstring | |
uri |
Abcstringnull | |
vendor |
Abcstringnull |
Get a single live stream output
| Parameter | Type | Description |
|---|---|---|
liveStreamId required |
Abcstring | live stream id |
liveStreamOutputId required |
Abcstring | live stream output id |
Update a live stream output
| Parameter | Type | Description |
|---|---|---|
liveStreamId required |
Abcstring | live stream id |
liveStreamOutputId required |
Abcstring | live stream output id |
LiveStreamOutputUpdatePayload required |
{ }object | |
asset_folder |
Abcstringnull | |
name |
Abcstringnull | |
public_id |
Abcstringnull | |
stream_key |
Abcstringnull | |
uri |
Abcstringnull |
Delete a live stream output
| Parameter | Type | Description |
|---|---|---|
liveStreamId required |
Abcstring | live stream id |
liveStreamOutputId required |
Abcstring | live stream output id |
Create a video generation job
Submits an image and prompt for video generation and returns a job you can poll for the result.
| Parameter | Type | Description |
|---|---|---|
request required |
{ }object | A JSON object with the source image, prompt, and generation options. |
aspect_ratio |
Abcstring | Video aspect ratio. |
duration |
#number | Video duration in seconds. |
enhance_prompt |
◉booleannull | Whether to let Cloudinary automatically enhance the prompt. |
folder |
Abcstring | Path of the folder to save the generated video to, for example |
generate_audio |
◉boolean | Whether to generate audio. Enabling audio consumes twice as many credits. |
image_asset_id required |
Abcstring | Cloudinary asset ID of the input image for image-to-video generation. |
last_frame_image_asset_id |
Abcstring | Cloudinary asset ID of the last frame image. |
negative_prompt |
[ ]array | Elements the video should avoid, for example |
prompt required |
Abcstring | Video description prompt. |
reference_image_asset_ids |
[ ]array | Cloudinary asset IDs of reference images. |
resolution |
Abcstring | Video resolution. |
Poll a video generation job
Returns the current status of a generation job. When the status is completed, the response includes the generated video's asset details and delivery URL.
| Parameter | Type | Description |
|---|---|---|
jobId required |
Abcstring | The video generation job ID returned from the create endpoint. |
Get a list of image to video prompts
Returns all saved image-to-video prompts for your product environment.
| Parameter | Type | Description |
|---|---|---|
request |
{ }object |
Create an image to video prompt
Saves a reusable prompt with a display name so you can apply it to future generations.
| Parameter | Type | Description |
|---|---|---|
request required |
{ }object | A JSON object with the prompt text and its display name. |
display_name required |
Abcstring | A human-readable name for the prompt. |
prompt required |
Abcstring | The prompt text describing the motion or scene to generate. |
Get an image to video prompt
Returns a single saved prompt by its ID.
| Parameter | Type | Description |
|---|---|---|
promptId required |
Abcstring | The ID of the image-to-video prompt. |
Update an image to video prompt
Updates the display name and/or prompt text of a saved prompt.
| Parameter | Type | Description |
|---|---|---|
promptId required |
Abcstring | The ID of the image-to-video prompt. |
ImageToVideoPromptUpdatePayload required |
{ }object | A JSON object with the fields to update (display name and/or prompt text). |
display_name |
Abcstringnull | A human-readable name for the prompt. |
prompt |
Abcstringnull | The prompt text describing the motion or scene to generate. |
Delete an image to video prompt
Permanently deletes a saved prompt by its ID.
| Parameter | Type | Description |
|---|---|---|
promptId required |
Abcstring | The ID of the image-to-video prompt. |
Create an AI Video Analysis job
Submits a stored video asset for visual analysis and returns a job you can poll for the result.
| Parameter | Type | Description |
|---|---|---|
request required |
{ }object | A JSON object with the video asset to analyze and optional analysis options. |
video_asset_id required |
Abcstring | Cloudinary asset ID of the input video to analyze. |
visual_transcription_prompt |
Abcstring | A natural-language instruction that guides the description style or focus, for example |
Poll an AI Video Analysis job
Returns the current status of an analysis job. When the status is completed, the response includes the generated visual transcript file's asset details and delivery URL.
| Parameter | Type | Description |
|---|---|---|
jobId required |
Abcstring | The AI Video Analysis job ID returned from the create endpoint. |