Skip to main content
Glama
lilyco-42

letsgal-ai MCP Server

by lilyco-42

letsgal-ai — AI-Assisted LetsGal Studio Creation Toolchain

Reverse-engineer the LetsGal Studio project format from scratch, turning it into something AI can create directly: One-line story DSL → fully runnable project (chapters/characters/scenes/branches/performances), with both CLI and MCP access, zero dependencies.

Why

LetsGal Studio is a desktop GUI editor (no MCP, no CLI), but everything it works with is just plain JSON on disk. This project fully programmatizes that format:

  • AI generates the script → one command compiles it into a project → Studio opens it and it just works (fine-tune performances/assets as needed)

  • Format is fully aligned with the official one (project.json / characters.json / scenes.json / chapters/*.json / assets/.manifest.json) — Studio opens it with zero errors, auto-fixes merged character expressions, and swaps assets naturally.

Quick Start

# 安装(无需依赖,直接 clone 或 npm link)
npm link                    # 或 node bin/letsgal-ai.js …

# 1. 初始化工程骨架
letsgal-ai init my-game --name "时间的河流"

# 2. 写故事(见 examples/example.dsl)→ 编译
letsgal-ai build story.dsl -o my-game --name "时间的河流"

# 3. 校验
letsgal-ai validate my-game

# 4. 用 LetsGal Studio 打开 my-game → 播放

MCP (Direct AI Agent Invocation)

letsgal-ai mcp     # stdio JSON-RPC 2.0,零依赖实现

Exposed tools:

Tool

Description

letsgal_init

Initialize project skeleton

letsgal_compile

Story DSL → full project (auto-registers characters/scenes)

letsgal_add_dialogue / letsgal_add_narration

Append dialogue/narration block

letsgal_validate

Validate structure + asset references

letsgal_register_asset

Register asset into .manifest.json

letsgal_list_chapters

Chapter/Fragment statistics

Any MCP client (Claude Code / DSH / custom) just configures node bin/letsgal-ai.js mcp.

CLI

letsgal-ai init <dir> [--name 标题]
letsgal-ai build <story.dsl> -o <dir> [--name 标题]
letsgal-ai validate <dir>
letsgal-ai list <dir>
letsgal-ai mcp

Use as a Library

import { compileStory, initProject, validateProject, applyCharacterFlow, dialogue, narration, scene } from '@lilyco-42/letsgal-ai';

Development

npm test        # 冒烟测试:init → build → validate → MCP 握手

License & Credits

  • This tool is MIT licensed; contains no assets. Generated projects can directly use LetsGal Studio's official template assets (bundled with the engine).

  • Reverse-engineering based on: LetsGal Studio v1.1.0 (Windows) installer + official template project.

Roadmap

  • Ren'Py-style code ↔ Block bidirectional conversion (aligned with the official code editor syntax)

  • Headless build (reuse official build-worker to produce web version)

  • lilyco (Rust) native component: lilyco-letsgal (see docs/lyco-integration.md)

-
license - not tested
Not graded
quality - not tested
C
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

  • OCR, transcription, file extraction, and image generation for AI agents via MCP.

  • Generate, edit, and deploy immersive 3D/WebGL web projects from any MCP assistant.

  • Hosted MCP for creating, checking, deploying, and hosting static sites for AI agents.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/lilyco-42/letsgal-ai'

If you have feedback or need assistance with the MCP directory API, please join our Discord server