Kids Book Maker

Custom children’s stories

Create something special for story time with your child. Kids Book Maker helps parents and other adults turn their ideas into narrated picture books for their children.

What you can ask

Create a bedtime story about a little fox learning to share.
·

MCP connector

Server URL: https://scrimba.com/explain/chatgpt/kids/mcp
Login: None
Protocol: MCP 2025-11-25
Instructions: Scrimba Kids Books creates narrated picture books for children, with an illustrated cover and a picture on every page. It can use the user's own drawings and photos as pages or as the look of a character.
For one focused explainer, use / / . Scrimba renders the explainer markup you push live. Use these tools for narrated picture books with storybook illustrations and the user's own uploaded pictures.
Check that you know which story to tell. A story idea, a theme, or a lesson for the child is enough. If the user supplied pictures, look at them before you start. If the request has no story idea at all, ask the user for one and wait before starting.
When you have a story idea, start immediately. Take the child's age, the characters, and the setting from the request, or choose them yourself; do not ask optional questions that delay the book.
The flow: initializes the stream and gives you a stream_token plus the explainer markup contract — no link yet. Your first successful returns the explainer's link; that first append is the viewer's playback buffer, not a handshake for the link — give it a real opening section, never just a title slide. When the link arrives, send it to the user as a non-blocking progress update and continue appending immediately, without waiting for a reply — they open it to watch the explainer get built live. The streaming and tokens are internal mechanics for YOU — don't narrate them to the user; just say you're creating their Scrimba explainer.
The second you call you will be given a full description of the streaming format that you can use to send in stream chunks. That result is large — more than 50KB, mostly the explainer markup contract — so if your client stores or truncates large tool results, use any storage or file tools you have to extract the result in full and read it to the end before pushing.

Tools

Changes data4

Skills

1 in the ChatGPT listing

Screenshots

MCP connector

Server URL

https://scrimba.com/explain/chatgpt/kids/mcp

None

Protocol

MCP 2025-11-25

Instructions

Scrimba Kids Books creates narrated picture books for children, with an illustrated cover and a picture on every page. It can use the user's own drawings and photos as pages or as the look of a character.

For one focused explainer, use / / . Scrimba renders the explainer markup you push live. Use these tools for narrated picture books with storybook illustrations and the user's own uploaded pictures.

Check that you know which story to tell. A story idea, a theme, or a lesson for the child is enough. If the user supplied pictures, look at them before you start. If the request has no story idea at all, ask the user for one and wait before starting.

When you have a story idea, start immediately. Take the child's age, the characters, and the setting from the request, or choose them yourself; do not ask optional questions that delay the book.

The flow: initializes the stream and gives you a stream_token plus the explainer markup contract — no link yet. Your first successful returns the explainer's link; that first append is the viewer's playback buffer, not a handshake for the link — give it a real opening section, never just a title slide. When the link arrives, send it to the user as a non-blocking progress update and continue appending immediately, without waiting for a reply — they open it to watch the explainer get built live. The streaming and tokens are internal mechanics for YOU — don't narrate them to the user; just say you're creating their Scrimba explainer.

The second you call you will be given a full description of the streaming format that you can use to send in stream chunks. That result is large — more than 50KB, mostly the explainer markup contract — so if your client stores or truncates large tool results, use any storage or file tools you have to extract the result in full and read it to the end before pushing.