In this tutorial, we'll set up Bannerbear MCP for OpenClaw so you can generate images, manage templates, and trigger workflows — all through plain text prompts. No code required.
We'll cover:
• What Bannerbear is and how the MCP integration works
• Getting your Bannerbear API key
• Connecting via remote server URL or local NPX
• Verifying the connection in OpenClaw
• Generating a single image and batch images from templates
• Inspecting and editing templates from chat
• Triggering multi-step Bannerbear workflows
What you'll need: OpenClaw installed, Node.js and NPM, and a Bannerbear account (free trial available — link below).
If you found this helpful, drop a like, subscribe, and let me know in the comments what you're planning to build!
● Sign up for Bannerbear - https://www.bannerbear.com/pricing/ ● Welcome to Bannerbear v5 - https://www.youtube.com/watch?v=3kWKsDK19G4
Video Transcription
[00:00:00] Hey everyone, welcome back. With the update to Bannerbear v5, you get a whole bunch of upgrades, like responsive templates, animations, workflows, and also MCP. We've covered those new features in our Welcome to Bannerbear v5 video, and also made setup guides for Bannerbear MCP in Claude Code and Codex. In today's video, we're going to set up Bannerbear MCP for OpenClaw.
Before we set anything up, let's quickly cover what Bannerbear is and what this MCP integration does. Bannerbear is a tool for automatically generating custom visuals from templates. Here's an example template open in the Bannerbear editor, and every
[00:01:00] template can have two kinds of elements: static objects, like a logo that stays the same every time, and dynamic objects, like text or images that change based on the data you feed in.
Bannerbear already offers APIs and SDKs in Node.js, Ruby, and PHP. But now with the MCP, you don't need to write any code yourself. You can generate images directly using plain text prompts inside your OpenClaw. Instead of calling an endpoint, just ask something like, "Find me a template suitable for Instagram," or, "Generate an image from this template using this text."
Your AI assistant will handle everything from pulling template details, validating your
[00:02:00] layers, to returning the final result. Okay, let's start setting it up. Here is what you'll need. You'll need three things: OpenClaw installed on your machine, Node.js and NPM installed, and a Bannerbear account. If you don't have a Bannerbear account, you can use the link in the description to get a free trial with 30 API credits.
First, we need an API key from Bannerbear. Log in to your Bannerbear dashboard and head to API keys. Create a new key or grab your existing one, and make sure it has permission to access your templates. Copy it somewhere safe. We'll need it later. Now, we can connect Bannerbear to
[00:03:00] OpenClaw. There are two options for this: using the remote server URL or running the server locally via NPX.
I'll show you both. To use the remote server URL, open your terminal and run this command with your own Bannerbear API key. If you need Bannerbear to access your file system, for example, to upload local files, go with the local NPX version with this command instead The MCP is added. Now let's make sure OpenClaw can actually use it and generate something.
Restart OpenClaw so it picks up the new MCP connection. Then ask it something simple like, "What Bannerbear
[00:04:00] tools do you have access to?" If everything's connected properly, OpenClaw will list out tools that the MCP can use, like list templates, get layer schema, generate image, and more in the CLI. Now that the basic connection works, let's make our first generation request and a handful of other things you can do, like generating a batch of images at once, checking a template's details, editing a template, and running a full body workflow You can ask OpenClaw something like, "Generate an image using the blue yellow gradient Tweetagram template with the title, 'Hello from OpenClaw.'"
[00:05:00]
Behind the scenes, OpenClaw will use all the tools needed to produce the image and return the result. If you want a whole batch of images at once, try something like this: "Generate a batch of 10 images from the blue yellow gradient template using different quotes about tech for each." OpenClaw will find the template, build the batch payload, and hand it off to the create batch tool.
Instead of 10 separate requests, all 10 variations get generated in one go. With the MCP, you can also inspect a template directly from OpenClaw without ever opening the editor. For example, you can check a template's details by asking, "How many objects are there
[00:06:00] in the blue yellow gradient Tweetagram template?"
OpenClaw will call the template's config and give you the answer in the chat directly. You can even edit the template without touching the editor On my blue-yellow gradient Tweetagram template, remove the username handle layer and add an object for author under the quote using the same font style and color, but smaller font size.
OpenClaw will pull the current config and update it based on your request. Last but not least, if you've already got a multi-step workflow set up in Bannerbear, you can trigger that from OpenClaw, too. Let's say you've got a multi-step workflow
[00:07:00] like this setup. You can trigger it from OpenClaw. Run my video editing workflow with this video.
OpenClaw will look up the workflow, trigger it, and return the result. And that's it. You've now got Bannerbear MCP connected to your OpenClaw. From here, you can do pretty much everything you'd normally do in your Bannerbear dashboard, just conversationally straight from OpenClaw. If you found this useful, drop a like, subscribe, and let me know in the comments what you're planning to build with this.
I'll see you in the next one.
