maimai-mcp
MCP server for MAIMAI DX arcade game, enabling song/score/statistics queries and image generation, accessible via command line or LLM agents.
README
maimai-mcp
本地可用的舞萌 DX 查询库 / CLI / MCP 服务:查曲、查分、进度与绘图,供命令行或 Agent 调用。
- 仓库:https://github.com/antinomie1/maimai-mcp
- 上游参考:Yuri-YuzuChaN/maimaiDX
- 绘图沿用原版布局与素材接口
能做什么
- 查曲、谱面信息、分数线
- 水鱼 b50 / 用户名查分;有开发者 Token 时可查更完整成绩
- 上分推荐、排名、今日运势等
- 定数表 / 完成表 / 牌子与等级进度
- 约 28 个 MCP tools;组合工具可内部串联(如搜歌 → 出图)
默认主题 circle;需要 prism_plus 时再显式切换。身份支持 QQ 或 水鱼用户名。
落雪查分器是可选的,不配也能用水鱼主流程。
目录
maimai_mcp/ 业务 + CLI + MCP(主包)
core/ 客户端、领域逻辑、原版 image
features/ 功能拆分(query / draw)
tools/ MCP 工具层
scripts/ Inspector、冒烟脚本
安装与配置
git clone https://github.com/antinomie1/maimai-mcp.git
cd maimai-mcp
pip install -e .
# ginfo 饼图需要:
# playwright install chromium
cp maimai_mcp/.env.example maimai_mcp/.env
maimai_mcp/.env 至少:
| 变量 | 说明 |
|---|---|
MAIMAIDX_PATH |
static 的绝对路径(必填) |
DIVINGFISH_TOKEN |
水鱼开发者 Token(强烈建议) |
DEFAULT_USERNAME / DEFAULT_QQ |
可选默认身份 |
LXNS_* |
仅在使用落雪时填写 |
资源包需自行下载(与 maimaiDX 相同),解压后指向 static:
请遵守上游美术相关声明。
首次若要用表类指令,生成一次表图:
python -m maimai_mcp.cli update tables
使用
CLI
# 未 install -e 时:export PYTHONPATH=.
python -m maimai_mcp.cli b50 --username <水鱼用户名> --out out/b50.png
python -m maimai_mcp.cli chart 834
python -m maimai_mcp.cli search --mode 定数 14.0 --format json
python -m maimai_mcp.cli user theme prism_plus --qq <QQ>
MCP
python -m maimai_mcp
MCP 由客户端拉起。配置示例(路径改成你的机器):
{
"mcpServers": {
"maimai": {
"command": "python",
"args": ["-m", "maimai_mcp"],
"cwd": "/path/to/maimai-mcp",
"env": {
"PYTHONPATH": "/path/to/maimai-mcp"
}
}
}
}
Windows 示例见 mcp.example.json。
联调
./scripts/run_inspector.ps1 # 或 run_inspector.sh
python scripts/smoke_mcp_tools.py --username <水鱼用户名>
刷新曲库
python -m maimai_mcp.cli update music
python -m maimai_mcp.cli update alias
致谢
- Yuri-YuzuChaN/maimaiDX — 绘图与业务参考
- Diving-Fish 查分器 — 成绩与曲库数据
- 落雪查分器 — 可选成绩数据源
- 柚子别名 — 曲目别名数据
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.