MCP Servers

galgame-mcp-engine

An MCP server that provides a visual novel world engine, enabling AI clients to drive interactive galgame experiences with narrative consistency.

README

旮旯给木里不是这样的 — MCP 版

Galgame 不是这样的。

一个视觉小说世界引擎，以 MCP Server 形式运行。任何支持 MCP 协议的 AI 客户端都能驱动它。

谁不想在公司摸鱼的时候来一场甜甜的恋爱呢。

与 skill 版的关系

这是 galgame_world_engine skill 的 MCP 重构版。

	Skill 版	MCP 版
运行方式	Reasonix subagent	独立 MCP Server
格式保证	提示词约束	代码强制
兼容性	仅 Reasonix	所有 MCP 客户端
状态管理	LLM 自觉维护	代码自动维护

MCP 版完全兼容 skill 版的 .game/ 存档，无需迁移。

安装

git clone https://github.com/mchenziyi/galgame-mcp-engine.git
cd galgame-mcp-engine
pip install -e .

依赖：Python 3.12+，DeepSeek API（由客户端调用，MCP Server 自身不调 LLM）。

配置

Reasonix

在项目根目录的 reasonix.toml 中添加：

[[plugins]]
name = "galgame-engine"
command = "python"
args = ["路径/galgame-mcp-engine/src/galgame_engine/server.py"]
env = { GALGAME_DIR = ".game" }

然后将项目根目录的 prompt.md 内容作为系统提示词使用。

重启 Reasonix，输入 /galgame_world_engine 开始。

Claude Desktop

{
  "mcpServers": {
    "galgame-engine": {
      "command": "python",
      "args": ["路径/galgame-mcp-engine/src/galgame_engine/server.py"],
      "env": { "GALGAME_DIR": "路径/你的/.game目录" }
    }
  }
}

Cursor / Windsurf

在 MCP 配置中添加同上的 stdio server 配置。

使用

安装并配置后，在 AI 客户端中调用 MCP tools：

Tool	说明
`galgame_start`	加载存档，返回完整世界上下文（角色/关系/时间线/谜团）
`galgame_action`	提交玩家操作，引擎校验叙事格式并自动维护存档
`galgame_status`	叙事口吻的世界状态摘要

推荐配合项目根目录的 prompt.md 使用——它定义了叙事品质标准、角色规则和决策优先级。适配各客户端的桥接配置见 galgame-is-not-like-this。

架构

prompt.md                   ← 通用叙事 prompt（叙事哲学、品质要求）
         │
         ▼
    AI 客户端（LLM）
         │ 生成叙事
         ▼
┌─────────────────────────────┐
│   galgame-engine (MCP)      │
│                             │
│  server.py      工具入口     │
│  engine.py      核心协调     │
│  state_manager  存档读写     │
│  response_builder 格式校验   │
└─────────────────────────────┘
         │
         ▼
    .game/ (4 个 JSON)

许可证

MIT

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.

Official

Featured

TypeScript

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.

Official

Featured

Local

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.

Official

Featured

TypeScript

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.

Official

Featured

Python

E2B

Using MCP to run code via e2b.

Official

Featured

Neon Database

MCP server for interacting with Neon Management API and databases

Official

Featured

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.

Official

Featured

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official

Featured