talebuilder-pluginSAFE
Make children's picture books from Claude, ChatGPT, Gemini and other AI assistants (TaleBuilder MCP server)
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Make children's picture books from Claude, ChatGPT, Gemini, Grok and other AI assistants. Describe an idea ("a shy owl who wants to sing in the forest choir, for a first grader") and TaleBuilder writes a ten-page story, draws the characters and the cover as a free preview, and can then illustrate every page.
For parents. Books are made on your TaleBuilder account: you sign in once when you connect, and every book shows up in your library on talebuilder.com.
Server URL: https://www.talebuilder.com/api/mcp (remote MCP, Streamable HTTP, OAuth sign-in)
Tools
A preview takes about 3 to 4 minutes; finishing a book takes about 8. The tools return right away with a link where you can watch the book being made.
Connect
You sign in to TaleBuilder in your browser the first time the assistant uses a tool. New here? You can create an account on that page.
Claude (claude.ai, Claude Desktop)
Settings, then Connectors, then Add custom connector. Paste https://www.talebuilder.com/api/mcp and connect.
Claude Code
As a plugin:
/plugin marketplace add tomkit/talebuilder-plugin /plugin install talebuilder@talebuilder
Or directly:
claude mcp add --transport http talebuilder https://www.talebuilder.com/api/mcp
Then run /mcp and choose TaleBuilder to sign in.
ChatGPT
Turn on Developer mode (Settings, then Security and login),
a2da69e8ab01OBSERVED · 2026-10-11Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (3)
streamable-http
assets/logo.png
Gates applied: no_behavioural_pass.
a2da69e8ab01full audit observations/trust-audit/mcp-server/tomkit__talebuilder-plugin.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | a2da69e8ab01 | SAFE | B | 89 | first audit |
Questions
What is the talebuilder-plugin MCP server?
Make children's picture books from Claude, ChatGPT, Gemini and other AI assistants (TaleBuilder MCP server)
Is talebuilder-plugin safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does talebuilder-plugin need?
No credential environment variables were found in its source, so it appears to need none.
How does talebuilder-plugin run?
It speaks streamable-http, so it runs as a service you connect to over the network.
How current is this page?
The grade is for one exact copy of the source (a2da69e8ab01), read on 2026-10-11. The repository is watched and re-audited when it changes.