Skip to main content
Glama
danmaps

Bedtime Book Studio

by danmaps
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PUBLISH_BASE_URLNoOptional base URL corresponding to PUBLISH_WEB_ROOT. Published book URLs are returned as <PUBLISH_BASE_URL>/<slug>.
PUBLISH_WEB_ROOTNoOptional path to a web server or static site folder where published books are automatically copied.
LOCAL_SERVER_PORTNoPort for the built-in local HTTP server used to serve published books. Configurable via LOCAL_SERVER_PORT in .env.8765

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
get_onboarding_statusA

Call this FIRST when starting a session. Checks whether the user has completed first-time onboarding in .env (main character name, reference photo(s) and/or text appearance description, outfit, art style, and default book mode). If is_onboarded is false, follow agent_onboarding_instructions to ask the user for their main character details and call configure_studio.

configure_studioC

Save or update user onboarding settings in the local gitignored .env file. Copies any main_character_photos into local_profile/references/ so every future book automatically has access to the main character's reference photo(s) and/or text description.

get_studio_profileB

Return the active studio profile from .env, including main character details (name, age, text description, outfit, reference photo paths), supporting cast, default art style, default book mode, and local hosting paths.

list_existing_booksA

List all bedtime picture-book projects in BOOKS_OUTPUT_DIR, their single-file HTML path, and local URLs.

create_book_projectB

Step 1: Initialize a new bedtime picture-book project workspace. Any omitted fields (mode, character_name, character_description, page_count) automatically inherit the user's defaults from .env, and default character reference photos are automatically copied alongside any book-specific reference_images.

save_book_storyboardB

Step 2: Save the complete storyboard.json for a book and generate prompts.md plus the exact list of required image keys (cover, page-01-reality, page-01-imaginary, ...).

ingest_generated_imagesA

Step 3: After generating illustrations (via subagents or image tools), pass a dictionary mapping asset keys (e.g. {"cover": "/path/to/img.jpg", "page-01-reality": "..."}) to normalize, center-crop to 1280x960 (4:3 landscape), and save both .png and .webp.

build_and_publish_bookA

Step 4: Compile the book into:

  1. A self-contained single-file HTML book (<slug>.html with all CSS, JS, and images embedded) that can be opened directly in any browser or AirDropped/shared to a phone or tablet.

  2. A multi-file web reader (index.html, styles.css, script.js, assets/).

  3. By default (serve_local=True), hosts the book immediately on the local device at http://localhost:<port>/<slug>/ and http://<lan-ip>:<port>/<slug>/ for phones on Wi-Fi.

  4. Optionally copies to PUBLISH_WEB_ROOT if the user configured custom self-hosting in .env.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.7/5.0

Scored across 8 tools

Disambiguation4/5

Most tools have clearly distinct roles, and the four pipeline steps (create_book_project, save_book_storyboard, ingest_generated_images, build_and_publish_book) are explicitly numbered, which strongly disambiguates them. The main overlap risk is between get_onboarding_status and get_studio_profile, which both read settings/profile data, though the descriptions distinguish the onboarding-check versus full-profile purposes.

Naming Consistency5/5

All eight tools follow a consistent snake_case verb_noun pattern (get_onboarding_status, list_existing_books, configure_studio, create_book_project, save_book_storyboard, etc.). The only mild deviation is the compound verb in build_and_publish_book, but it still fits the convention.

Tool Count5/5

Eight tools is well-scoped for a book-production pipeline spanning onboarding, project setup, storyboarding, image ingestion, and publishing. Each tool maps to a distinct stage and none appears redundant or filler.

Completeness4/5

The surface covers a full create-to-publish lifecycle including onboarding configuration and listing existing books. Minor gaps exist — no explicit tool for editing/regenerating an existing storyboard or deleting/archiving a book — but the core end-to-end workflow is intact.

Maintenance

ActivityMaintained
ResponsivenessUnresponsive

Resources