letsgal-ai MCP Server
Enables AI agents to programmatically create and manage LetsGal Studio visual novel projects via a story DSL, supporting project initialization, story compilation, dialogue/narration addition, validation, and asset registration through MCP tools.
README
letsgal-ai — AI 辅助 LetsGal Studio 创作工具链
从零逆向 LetsGal Studio 工程格式,把它变成 AI 可以直接创作 的工具: 一行式故事 DSL → 完整可运行工程(章节/角色/场景/分支/演出),CLI 与 MCP 双通道,零依赖。
- 格式参考(逆向自官方模板 + 1.11.0 安装包):docs/letsgal-format.md
- 故事 DSL 规范:docs/STORY-DSL.md
为什么
LetsGal Studio 是桌面 GUI 编辑器(无 MCP、无 CLI),但它的一切都是磁盘上的普通 JSON。 本项目把该格式完全程序化:
- AI 生成剧本 → 一行命令编译成工程 → Studio 打开即玩(可再精修演出/素材)
- 格式完全对齐官方(project.json / characters.json / scenes.json / chapters/*.json / assets/.manifest.json), Studio 打开零报错,自动修复合入角色表情、替换素材都自然
快速开始
# 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(AI Agent 直接调用)
letsgal-ai mcp # stdio JSON-RPC 2.0,零依赖实现
暴露工具:
| 工具 | 说明 |
|---|---|
letsgal_init |
初始化工程骨架 |
letsgal_compile |
故事 DSL → 完整工程(自动注册角色/场景) |
letsgal_add_dialogue / letsgal_add_narration |
追加对白/旁白 Block |
letsgal_validate |
校验结构 + 资产引用 |
letsgal_register_asset |
登记资产到 .manifest.json |
letsgal_list_chapters |
章节/Fragment 统计 |
任何 MCP 客户端(Claude Code / DSH / 自研)配置 node bin/letsgal-ai.js mcp 即可。
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
作为库使用
import { compileStory, initProject, validateProject, applyCharacterFlow, dialogue, narration, scene } from '@lilyco-42/letsgal-ai';
开发
npm test # 冒烟测试:init → build → validate → MCP 握手
授权与致谢
- 本工具 MIT;不含素材。生成的工程可直接使用 LetsGal Studio 官方模板素材(随引擎提供)
- 逆向依据:LetsGal Studio 1.11.0(Windows)安装包 + 官方模板工程
Roadmap
- [ ] Ren'Py 风格代码 ↔ Block 双向转换(对齐官方代码编辑器语法)
- [ ] 无头构建(复用官方 build-worker 产出 web 版)
- [ ] lilyco(Rust)原生组件:
lilyco-letsgal(见 docs/lyco-integration.md)
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.