Integration · Documents

Connect Claude & ChatGPT to Bannerbear

Ask your AI to fill a Bannerbear template with new text and images, or to turn a batch of rows into social graphics. It can read your templates and their layers, generate images and videos, run saved workflows and use the media tools for slideshows, subtitles, resizing, trimming, PDFs and background removal. Rendering runs in the background, and the AI checks back for the finished files.

Connect Bannerbear free

Free plan, no credit card. Takes about a minute.

Try asking

“Make an Instagram image from our sale template with the headline '30% off this weekend'.”
The AI reads the template's layers, fills in the headline and generates the image. When the render is done, it gives you the image URL.
“Create one image per product in this list using the product card template.”
It sends an image batch with one item per product and checks the batch until all images are ready.
“Turn these four product photos into a short video slideshow.”
It creates a slideshow from the image URLs in order and returns the video URL when the job is finished.

What your AI can do

Images and videos from templates

Read templates and their layers, generate single images, image batches and animations, and fetch finished files.

Workflows and instant URLs

Run saved workflows and check their output, and create instant URLs that render images from link parameters.

Media tools

Make video slideshows, add subtitles, resize or trim videos, combine files into a PDF and remove image backgrounds.

“Add subtitles to this video: https://example.com/clip.mp4”
It burns automatic subtitles into the video and returns the new file when the job is done.
“Remove the background from this product photo.”
It creates a new image with a transparent background. The original is not changed.
“Run our blog header workflow with the title 'Spring checklist'.”
It runs the saved workflow with the inputs it expects and checks the run for the output files.

28 tools for Bannerbear

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

add_video_subtitlesChanges dataBurn automatic subtitles into a video at `video_url`. Optional language, font, colours and words per segment. Runs async: poll get_tool_job.
create_animationChanges dataRender a video from an animation template. Pass `template` (UID) and `modifications` for the layers to change; optional formats. Rendering is async: poll get_animation.
create_imageChanges dataGenerate an image from a template. Pass `template` (UID) and `modifications` with the layer objects to change (e.g. text or image URLs by layer name); optional formats (jpg, png, pdf, webp). Rendering is async: poll get_image for the finished file URL.
create_image_batchChanges dataGenerate many images in one request. Pass `type` images and `items`, each with a `template` UID and `modifications`. Poll get_image_batch for results.
create_instant_urlChanges dataCreate an instant URL for a template, so images can be rendered by changing link parameters. Pass `name` and `template` UID; optional expiry and render limits.
create_pdfChanges dataCombine files at a list of `urls` into one PDF. Runs async: poll get_tool_job.
create_video_slideshowChanges dataMake a video slideshow from two or more `image_urls` in order. Optional width, height, slide_duration and transition. Runs async: poll get_tool_job.
get_accountGet the connected Bannerbear account details and usage. Use to confirm which account you are working in.
get_animationGet one rendered animation by `uid`: status and, when finished, the video URLs.
get_animation_templateGet one animation template by `uid`, including its layers, so you know what you can change.
get_imageGet one generated image by `uid`: its render status and, when finished, the image URLs.
get_image_batchGet one image batch by `uid`, with its status and the generated images.
get_image_templateGet one image template by `uid`, including its layers (objects) and their names, so you know which layers you can change.
get_instant_urlGet one instant URL by `uid`, with its base link and settings.
get_tool_jobGet one media tool job by `uid`: status and the output file URL when finished.
get_workflowGet one workflow by `uid`, including its steps and the inputs it expects.
get_workflow_runGet one workflow run by `uid`: status and output files when finished.
list_animation_templatesList your animation (video) templates, page by page.
list_animationsList animations (videos) you have rendered, page by page.
list_image_templatesList your image templates, page by page. Use to find a template UID before generating an image.
list_imagesList images you have generated, page by page, newest first.
list_instant_urlsList your instant URLs (links that render an image from a template on the fly from URL parameters).
list_tool_jobsList media tool jobs (slideshows, subtitles, resizes, trims, PDFs, background removal), page by page.
list_workflowsList your workflows (saved multi-step media pipelines), page by page.
remove_image_backgroundDeletesRemove the background from an image at `image_url`, returning a new image with a transparent background. The original is not changed. Runs async: poll get_tool_job.
resize_videoChanges dataResize a video at `video_url` to `width` x `height` pixels, with optional fit mode. Runs async: poll get_tool_job.
run_workflowChanges dataRun a saved workflow. Pass `workflow` (UID) and the `inputs` it expects. Runs async: poll get_workflow_run.
trim_videoChanges dataCut a video at `video_url` to the part between `start` and `end`. Runs async: poll get_tool_job.

Set up in three steps

1
Pick the app
Create a free PipMCP account and choose Bannerbear from the app list.
2
Paste your key
Paste a Bannerbear V5 API key. Open app.bannerbear.com/v5/api_keys, create an API key (you can scope it, for example to images:write) and copy it. V5 keys do not work with the old V2 endpoints.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in Bannerbear?

It can read your account, image and animation templates, generated images, image batches, animations, instant URLs, workflows and media tool jobs. It can generate images, image batches and animations, run workflows, create instant URLs, and make slideshows, subtitled, resized or trimmed videos, PDFs and background-free images.

Does the AI see my Bannerbear API key?

No. Your Bannerbear API key is encrypted at rest and never shown to the AI. After you save it, it is not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on, so you can let the AI read templates without generating anything. Actions that use renders, like generating images or running workflows, can require your approval before they run. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT, open Settings › Apps & Connectors › Advanced, turn on Developer mode and add your PipMCP link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

PipMCP has a free plan, and you do not need a credit card to start. Paid plans are billed per completed task. You also need your own Bannerbear account.

Why does the AI check back after starting a render?

Bannerbear renders images, videos and other files in the background. The AI starts the job, then fetches it again until the status shows it is finished and the file URL is ready.