IMPLEMENTATION
Call this tool
Connect a user's Bannerbear account once, then configure and run Create Video from your backend or agent.
import { PipedreamClient } from "@pipedream/sdk"
const pd = new PipedreamClient({
projectId: process.env.PIPEDREAM_PROJECT_ID!,
clientId: process.env.PIPEDREAM_CLIENT_ID!,
clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
projectEnvironment: "production",
})
const result = await pd.actions.run({
id: "bannerbear-create-video",
externalUserId: "{external_user_id}", // any stable ID for this user in your system
configuredProps: {
bannerbear: { authProvisionId: "apn_xxxxxxx" },
videoTemplate: "Video Template UID",
modifications: "Modifications",
},
})
console.log(result)curl -X POST https://api.pipedream.com/v1/connect/{project_id}/actions/run \
-H "Content-Type: application/json" \
-H "X-PD-Environment: production" \
-H "Authorization: Bearer {access_token}" \
-d '{
"external_user_id": "{external_user_id}",
"id": "bannerbear-create-video",
"configured_props": {
"bannerbear": { "authProvisionId": "apn_xxxxxxx" },
"videoTemplate": "Video Template UID",
"modifications": "Modifications"
}
}'// accessToken: mint a short-lived token with the Connect SDK — see the MCP guide
const transport = new StreamableHTTPClientTransport(
new URL("https://remote.mcp.pipedream.net/v3"),
{
requestInit: {
headers: {
Authorization: `Bearer ${accessToken}`,
"x-pd-project-id": "{project_id}",
"x-pd-environment": "production",
"x-pd-external-user-id": "{external_user_id}", // any stable ID for this user in your system
"x-pd-app-slug": "bannerbear",
},
},
},
)
const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)
const { tools } = await mcp.listTools()
// listTools() hands your model this tool's input schema, so it can
// fill the arguments itself:
const result = await mcp.callTool({
name: "bannerbear-create-video",
arguments: {
videoTemplate: "Video Template UID",
modifications: "Modifications",
},
})SCHEMA
Inputs
Pipedream supplies the connected account. Your application provides the operation-specific values below. Dynamic inputs are resolved against that user's account.
| Property | Type | Description |
|---|---|---|
videoTemplate Video Template UID | string | The video template UID that you want to use. See the docs Required Dynamic |
modifications Modifications | string | A list of modifications you want to make. See Create an image for more details on the child parameters. Unlike an Image the modifications list is not always required for a Video, for example: [{"name": "message", "text": "test message"}]. Required |
inputMediaUrl Input Media URL | string | Full url to a video or audio file you want to import as the background of the video. You can also use a static image, and the zoom parameter will be set automatically. This is required depending on the build pack of the template you are using: Build Pack: (Overlay: Input Media URL is required, Transcribe: Input Media URL is required, Multi Overlay: Input Media URL is optional) Required |
zoom Zoom | string | Apply a panning zoom effect to the video or image, can be one of: center, top, right, bottom, left. Optional |
zoomFactor Zoom Factor | integer | Amount to zoom in by from 1 to 100. If Zoom is set and Zoom Factor is left blank, this will default to 10. Optional |
blur Blur | integer | Apply a blur filter (from 1 to 10) to the incoming video. Optional |
trimStartTime Trim Start Time | string | Trim the Input Media URL clip to a specific start point, using HH:MM:SS notation. Optional |
trimEndTime Trim End Time | string | Trim the Input Media URL clip to a specific end point, using HH:MM:SS notation. Optional |
trimToLengthInSeconds Trim To Length In Seconds | integer | Force trim the end video to a specific time. There are two ways to trim videos, either you use Trim To Length In Seconds to trim from the start point by specifying a desired length. Or you can use Trim Start Time and Trim End Time to specify a part of the video / audio to be used. Optional |
webhookUrl Webhook URL | string | A url to POST the full Video object to upon rendering completed Optional |
metadata Metadata | string | Any metadata that you need to store e.g. ID of a record in your DB. Optional |
REFERENCE
Tool details
Behavior hints are published with the component in the Pipedream registry and surface as MCP tool annotations, so an agent can reason about a tool before it calls it.
- Registry key
- bannerbear-create-video
- Version
- 0.0.3
- App
- Bannerbear
- Authentication
- API key
- Read-only
- No
- Destructive
- No
- Open world
- Yes
- Source
- View on GitHub ↗