Integration

Shotstack integration

Shotstack is a cloud video editing API. An agent can render a video, image or audio file from a JSON edit (a timeline of tracks and clips with an output format) and wait for the finished file URL, save edits as reusable templates and render them with merge fields, inspect a media file's metadata, generate a single AI image, video or audio asset from a prompt, read and delete hosted assets, and fetch remote source files into Shotstack storage. Not included: the direct upload route, which hands back a signed URL the file must then be sent to. Every call uses the production (v1) environment; authentication is the production API key from the Shotstack dashboard, sent in the x-api-key header (sandbox stage keys are not accepted on v1). Rendering and generation consume account credits.

Connect Shotstack How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Shotstack.Built from the 22 Shotstack tools below, on the connection you add once.

What you can do with Shotstack

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Template, 5 operations

create_templateCreate templatePOSTSaves an edit (timeline + output) as a reusable template under a name; returns the template id for render_template. Placeholders like {{NAME}} in the edit are filled by merge fields at render time.
delete_templateDelete templateDELETEDeletes a saved template by its id (from list_templates). This cannot be undone.
get_templateGet templateGETGets a saved template by its id (from list_templates), including its name and the stored edit.
list_templatesList templatesGETLists the templates saved in the account, with their ids and names, for render_template or get_template.
update_templateUpdate templatePUTReplaces a saved template's name and edit, by template id (from list_templates). The vendor requires the name on every update.

Asset, 4 operations

delete_assetDelete assetDELETEDeletes a hosted asset by its asset id. A render's thumbnail and poster are separate assets, each deleted on its own. This cannot be undone.
get_assetGet assetGETGets a hosted asset (video, image, audio, thumbnail or poster) by its asset id: its status, hosted url and the render it came from.
list_render_assetsList render assetsGETLists the hosted assets (video, thumbnail, poster) a render produced, by the render id from render_edit or render_template. Use the asset ids for get_asset or delete_asset.
transfer_assetTransfer assetPOSTTransfers a file at a public URL to one or more Serve API destinations (Shotstack hosting or a connected third-party destination); returns the asset records.

Source, 4 operations

delete_sourceDelete sourceDELETEDeletes an ingested source file by its id (from fetch_source or list_sources). This cannot be undone.
fetch_sourceFetch sourcePOSTQueues a file at a public URL (video, image, audio or font) to be fetched into Shotstack storage; returns the source id. Poll get_source until its status is ready.
get_sourceGet sourceGETGets a source file by its id (from fetch_source or list_sources): its status, hosted url, size, dimensions, duration and any renditions.
list_sourcesList sourcesGETLists the source files fetched or uploaded into the account's Shotstack storage, with their status, hosted url and media details.

Generation, 3 operations

generate_assetGenerate assetPOSTGenerates one AI image, video or audio asset from a prompt (or a source file for some models); returns the job status and asset url. Billed in credits. Waits for the job and returns the finished result; gives up after 10 minutes.
get_generationGet generationGETGets the status (queued, processing, done, failed) of an AI generation job by the id generate_asset returned, with the asset url once done or the error once failed.
quote_generationQuote generationPOSTEstimates the credits a generate_asset call with the same asset and length would cost. Reserves nothing and generates nothing; a cached result costs nothing.

Render, 3 operations

get_renderGet renderGETGets the status (queued, fetching, rendering, saving, done, failed), temporary file url and details of a render, by the render id returned by render_edit or render_template.
render_editRender editPOSTRenders a JSON edit (timeline + output) as a video, image or audio file; returns the render status and the file url. Consumes render credits. Waits for the job and returns the finished result; gives up after 10 minutes.
render_templateRender templatePOSTRenders a saved template (id from list_templates) with optional merge fields; returns the render status and the file url. Consumes render credits. Waits for the job and returns the finished result; gives up after 10 minutes.

Model, 2 operations

get_modelGet modelGETGets one AI generation model, with the JSON Schema of the options it accepts and whether it is available to this account. Use quote_generation for a credit estimate.
list_modelsList modelsGETLists the AI generation models available to this account for image, video and audio assets; set expand=options to include each model's option schema.

Media, 1 operation

probe_mediaProbe mediaGETInspects a media file (image, video, audio) at a public URL with a hosted FFprobe and returns its metadata (streams, duration, dimensions, codecs) as FFprobe JSON.

Use Shotstack from Claude Code, Cursor or Codex

Connect Shotstack in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Shotstack operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Shotstack

Create your workspace
Sign up free. Nothing to install.
Connect Shotstack once
Add your Shotstack connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.