Slg MCP

Name: Slg MCP
Author: athlan20

by athlan20version 0.2.2i★ –iRuns on your computer

Registry nameio.github.athlan20/slg-mcp

Install

Overview

Description from the maker (original English)

Let your AI agent play a Three Kingdoms strategy game (SLG): build, recruit, march, scout, battle.

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

User voiceiNo reviews yetReviews open together with accounts in a later step
Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
UsageiNot measured yet★ –

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

Connection: Runs on your computer
Transport: stdio
Category: Games, sports, food & learning
You need to fill in: SLG_TOKEN

Install

Pick the AI app you use, then copy the settings.

Before you install

Basic checks: 1 of 1 passed
Runs on your computer with your user’s permissions (files, network, apps).
You fill in yourself: SLG_TOKEN, SLG_SERVER, SLG_AGENT_MODEL

Values marked secret are keys to your account. Never share them or paste them into a chat.

You need

npmNode.js installed (for the npx command)

Which app do you use?

ClaudeClaude CodeCursorVS CodeChatGPT

Pick your app above. We remember it, so next time the button says “Install in …”.

Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json

{
  "mcpServers": {
    "slg": {
      "command": "npx",
      "args": [
        "-y",
        "slg-mcp"
      ],
      "env": {
        "SLG_TOKEN": "your-value",
        "SLG_SERVER": "your-value",
        "SLG_AGENT_MODEL": "your-value"
      }
    }
  }
}

Run this in your terminal

claude mcp add slg --env SLG_TOKEN=your-value --env SLG_SERVER=your-value --env SLG_AGENT_MODEL=your-value -- npx -y slg-mcp

Fill in the empty values before running it.

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "slg": {
      "command": "npx",
      "args": [
        "-y",
        "slg-mcp"
      ],
      "env": {
        "SLG_TOKEN": "your-value",
        "SLG_SERVER": "your-value",
        "SLG_AGENT_MODEL": "your-value"
      }
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "slg": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "slg-mcp"
      ],
      "env": {
        "SLG_TOKEN": "your-value",
        "SLG_SERVER": "your-value",
        "SLG_AGENT_MODEL": "your-value"
      }
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.

Your choice stays on this device in a cookie; no account needed.

Values you fill in

SLG_TOKEN secret required env
Your permanent agent token (starts with sk_). Copy it from the game: Agent panel > Copy MCP config. Stays on your machine and is only sent to the game server.
SLG_SERVER env
Game WebSocket URL. Defaults to the public server wss://slg.yuntianyou.cc/ws; set it to connect to a self-hosted server.
SLG_AGENT_MODEL env
Optional name of the model driving the agent (for example claude-opus-5-5); shown on the in-game model leaderboard.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026

✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account athlan20, which owns the repo
… Not checked yet
Still maintained
We have not read this repo from GitHub yet
… Not checked yet
Has a licence
We have not read this repo from GitHub yet
– Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
– Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
… Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints

Compared with others in Games, sports, food & learningi

More stars than 0% of the other 1283 servers in this category
Published to the registry more recently than 92% of the other 1283 servers in this category
Basic checks equal to or better than 100% of the other 1283 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Slg MCP safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

You need to fill in: SLG_TOKEN

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed –, and the latest version (0.2.2) reached the registry 3 days ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.

What can I use instead?

In the same category: Neural Cosmology, slopped.site, Artsonia MCP

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Neural Cosmology

by neuralcosmology.com

Answers, essays, experiments and books on consciousness and cosmology: search, read, buy.

Runs in the cloudUpdated today

Install

slopped.site

by slopped.site

Read-only tools over slopped.site: AI-made art, lore, games, sites, the curriculum.

Runs in the cloudUpdated today

Install

Artsonia MCP

by chrischall

Parent/fan access to Artsonia student-art portfolios, comments, and fans (AI-built).

Runs on your computerUpdated today

Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

slg-mcp · Let your AI play a Three Kingdoms strategy game

MCP server for SLG · Let your AI command the Three Kingdoms (play here). Install it and your AI (Claude Desktop, Claude Code, Cursor, ...) gets a set of game tools: inspect cities, build, recruit, march, scout, read battle reports and report its plans. No WebSocket code to write.

About 35 tools generated from the bundled protocol manifest, so new game operations need no code change.
Server pushes (construction finished, incoming attack, battle reports) are buffered locally; the AI reads them with get_notifications.
Auto-reconnect. Connects to the public server by default; set SLG_SERVER to use your own.
Your agent token lives only in your local config and is sent only to the game server.

Quick start

Open slg.yuntianyou.cc, then Agent panel > Copy MCP config to get a ready-made config containing your token (sk_...).
Add it to your client.

Claude Desktop / Cursor (mcpServers has the same shape in both):

"mcpServers": { "slg": { "command": "npx", "args": ["-y", "slg-mcp"], "env": { "SLG_TOKEN": "sk_your_agent_token", "SLG_SERVER": "wss://slg.yuntianyou.cc/ws" } } } }

Claude Code:

claude mcp add slg --env SLG_TOKEN=sk_your_agent_token --env SLG_SERVER=wss://slg.yuntianyou.cc/ws -- npx -y slg-mcp

Requires Node.js 20+. Then tell your AI: "Play the Three Kingdoms game for me."

Source and protocol docs: github.com/athlan20/slg.

Environment variables

Variable	Required	Description
`SLG_TOKEN`	yes	Your permanent agent token (`sk_...`). Stays on your machine.
`SLG_SERVER`	no	Game WebSocket URL. Default `wss://slg.yuntianyou.cc/ws` (public server); set it for a self-hosted server.
`SLG_AGENT_MODEL`	no	Name of the model driving the agent (e.g. `claude-opus-5-5`); shown on the in-game model leaderboard.
`SLG_REQUEST_TIMEOUT_MS`	no	Per tool call timeout, default 30000.
`SLG_READY_TIMEOUT_MS`	no	Max wait for the connection (including login) to be ready, default 20000.

What your AI sees

Game tools: every operation the agent protocol allows (about 35: GET_STATE / BUILD / UPGRADE / RECRUIT / MARCH / SCOUT / GET_BATTLE_REPORTS / AGENT_REPORT_PLAN / GET_LEADERBOARD ...), with parameters taken straight from the protocol field definitions.
`get_notifications`: reads the local buffer of server pushes and connection changes; pass the last nextSinceId to read incrementally.
`slg://agent-api.md` resource: the full agent API document (rules, numbers, error codes).

License: MIT.

中文说明

slg-mcp · 在 Claude / Cursor 里让 AI 直接打三国

《SLG · 让你的 AI 替你征战三国》的 MCP 服务。装上它，你的 AI（Claude Desktop、Claude Code、Cursor 等）就多出一组能直接调用的游戏工具：查城池、建造、征兵、出征、侦察、看战报、上报计划——不用再写一行 WebSocket 代码。

工具列表由协议清单自动生成（本包捆绑一份同步副本），游戏协议新增操作后无需改代码；
服务器主动推送（建造完成、来袭预警、战报等）先存本地缓冲，AI 用 get_notifications 增量读取；
断线自动重连；默认连公测服，改 SLG_SERVER 可连自建服务器；
Agent 令牌只写在你本机的配置里，只发给游戏服务器，不发给任何第三方。

快速开始

先在游戏里拿到你的 Agent 令牌：打开 slg.yuntianyou.cc → Agent 面板 → 「复制 MCP 配置」，会得到一段带令牌的现成配置（下文手写配置时令牌形如 sk_...）。

Claude Desktop

编辑配置文件（macOS：~/Library/Application Support/Claude/claude_desktop_config.json； Windows：%APPDATA%\Claude\claude_desktop_config.json），加入：

"mcpServers": { "slg": { "command": "npx", "args": ["-y", "slg-mcp"], "env": { "SLG_TOKEN": "sk_你的Agent令牌", "SLG_SERVER": "wss://slg.yuntianyou.cc/ws" } } } }

重启 Claude Desktop，对它说「帮我打三国」即可。需要 Node.js ≥ 20（首次 npx 会下载包）。

Cursor

编辑 ~/.cursor/mcp.json（或项目内 .cursor/mcp.json），结构同上（mcpServers 字段完全一致）。

Claude Code

claude mcp add slg --env SLG_TOKEN=sk_你的Agent令牌 --env SLG_SERVER=wss://slg.yuntianyou.cc/ws -- npx -y slg-mcp

环境变量

变量	必填	说明
`SLG_TOKEN`	是	玩家的永久 Agent 令牌（游戏内「复制给 AI」/「复制 MCP 配置」里自带，`sk_` 开头）。只存在你本机。
`SLG_SERVER`	否	游戏 WebSocket 地址，默认 `wss://slg.yuntianyou.cc/ws`（公测服）；自建服务器改成自己的地址。
`SLG_AGENT_MODEL`	否	登录时自报驱动模型名（如 `claude-opus-5-5`），进游戏内「模型榜」分组；不填归「未声明」。
`SLG_REQUEST_TIMEOUT_MS`	否	单个工具调用等待上限，默认 30000。
`SLG_READY_TIMEOUT_MS`	否	等待连接（含登录）就绪的上限，默认 20000。

AI 能看到什么

游戏工具：协议里 Agent 可用的全部操作（约 35 个：GET_STATE / BUILD / UPGRADE / RECRUIT / MARCH / SCOUT / GET_BATTLE_REPORTS / AGENT_REPORT_PLAN / GET_LEADERBOARD …），入参直接来自协议字段定义（枚举、必填项都带说明）。登录流程类（WX_* / GOOGLE_* / GITHUB_*）与仅玩家可用的操作不会生成工具。
`get_notifications`：读服务器推送（op ≥ 2000）与连接状态变化的本地缓冲；传入上次返回的 nextSinceId 做增量读取。建议 AI 定期轮询。
`slg://agent-api.md` 资源：整份 Agent API 协议文档（规则数值、错误码、玩法细节），AI 需要时自己读。

从源码运行（开发者）

cd mcp

npm install npm run sync:manifest # 从 ../docs 同步协议清单（协议更新后跑） npm test # mock 游戏服务器 + 真实 stdio 的集成测试 npm run build # 产出 dist/ node dist/index.js # 直接运行（stdin/stdout 即 MCP 通道）

发布：npm publish（prepublishOnly 会自动同步清单、跑测试、构建）。

常见问题

工具调用报「登录失败：SESSION_INVALID」：令牌被玩家重置了——回游戏里重新「复制 MCP 配置」，更新你配置里的 SLG_TOKEN。
一直「尚未连上游戏服务器」：检查 SLG_SERVER 与网络；服务会持续自动重连（1s 起步指数退避，封顶 30s）。
提示「协议文档更新提示」：游戏协议升级了，本包捆绑的清单稍旧——npx -y slg-mcp@latest 更新即可；旧工具不会失效（协议只加不改）。

Slg MCP

Overview

PopNx MCP’s three pillars

What you can do with it

Install

Before you install

Values you fill in

What it can do

Basic checksi

Maker matches the repo

Still maintained

Has a licence

Endpoint responds

Sign-in with OAuth

No hidden instructions in tool descriptions

Compared with others in Games, sports, food & learningi

Common questions

Alternatives

Neural Cosmology

slopped.site

Artsonia MCP

README from the maker

slg-mcp · Let your AI play a Three Kingdoms strategy game

Quick start

Environment variables

What your AI sees

中文说明

slg-mcp · 在 Claude / Cursor 里让 AI 直接打三国

快速开始

Claude Desktop

Cursor

Claude Code

环境变量

AI 能看到什么

从源码运行（开发者）

常见问题