Skip to main content
Glama
wangyafu

Haiguitang MCP Server

by wangyafu
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

介绍

本项目旨在让大语言模型扮演海龟汤游戏主持人，使你独自一人也能享受海龟汤游戏的快乐。

Related MCP server: mcp-llm

快速开始

在使用本项目前，你需要确保你的电脑上已经安装了Python和uv。

你首先需要克隆整个项目，然后运行uv sync安装依赖。

git clone https://github.com/wangyafu/haiguitangmcp/
cd haiguitangmcp
uv sync

其次，你需要修改配置文件（假设你将项目安装在了E盘）

在vscode中配置

"mcp":{
    "servers":{
        "haiguitang-mcp": {
                "type": "stdio",
                "command": "uv",
                "args": [
                    "--directory",
                    "E:\\haiguitangmcp\\haiguitang_mcp",
                    "run",
                    "server.py"
                ]
            }
    }
}

在cherry studio中进行配置

"mcpServers": {
    
    "haiguitang": {
      "isActive": true,
      "name": "海龟汤MCP服务器",
      "description": "和用户玩海龟汤",
      "registryUrl": "",
      "command": "uv",
      "args": [
        "--directory",
        "E:/haiguitangmcp/haiguitang_mcp",
        "run",
        "server.py"
      ]
    },
   
}

上述的"E:/haiguitangmcp/haiguitang_mcp"表示server.py所在的路径。

在其他mcp client中的配置方法类似。

mcp相关内容

本项目提供了三个工具:

  • get_prompt: 获取海龟汤游戏的完整玩法说明

  • get_puzzle: 获取一个特定谜题的完整内容，需要提供谜题标题作为参数

  • list_puzzles_tool: 列出所有可用的谜题列表

同时，本项目还提供了以下资源:

  • puzzles://{puzzle_title}: 获取特定谜题的信息

以及一个提示模板:

  • game_rules: 提供海龟汤游戏规则的提示模板

游戏规则

在本游戏中：

  • 海龟汤是一种情景推理游戏，谜题本身并没有很强的逻辑性，注重能否发现关键线索重现情景

  • 出题人提出一个看似不合常理的问题和情景（谜面），猜题者通过提问缩小范围并最终揭示完整故事情节（谜底）

  • 猜题者可以提出任何问题，出题人主要用"是"、"不是"、"是也不是"或"没有关系"来回答

  • 当问题中既有对的地方也有不对的地方时，出题人会回答"是也不是"

  • 当问题与谜题核心情节无关时，出题人会回答"没有关系"

  • 猜题者可以通过在消息开头加上"汤底"来尝试描述完整情景

  • 当猜题者掌握了关键线索时，出题人会提醒猜题者归纳线索，形成对谜底的完整描述

  • 猜题者可以请求引导和提示，出题人会给予尚未掌握的线索

  • 当猜题者的描述大致包含了谜题的关键情景时，出题人会确认"完全正确"

小技巧

  • 从基本问题开始，如谜题涉及人数、死者的死因等。

  • 注意谜面中的每一个细节，它们可能是关键线索

  • 当你感到困惑时，尝试从不同角度思考问题

  • 记录已经确认的线索，以便归纳整理

关于谜题

目前本项目已经提供了35个谜题。 本人曾开发海龟汤模拟器，该网站有评分功能。目前的35个谜题来自于我和一些热心用户为该网站搜集的谜题。依据该网站上各谜题的评分，推荐游玩的谜题如下：

  • 忠诚的狗

  • 100元钱

  • 爱犬

  • 治病

  • 祭日

  • 电梯里的人

  • 延迟死亡

  • 生意

  • 裤子破了

  • 要好的朋友

欢迎你为本项目贡献更多的谜题。你可以在haiguitang_mcp/puzzles文件夹中加入新的谜题文件然后发起Pull Request。

注意：

  • 如果你希望用户游玩之前有所预警，你可以在标题，也就是谜题文件的名称中注明。

  • 请注意海龟汤的版权问题。

  • 你可以在海龟汤文件中添加作者和提交者信息。

Available Tools

3 tools
get_promptB

获取海龟汤游戏的玩法

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It only states what the tool does ('获取海龟汤游戏的玩法') without describing how it behaves: e.g., whether it returns static instructions, dynamic content, requires authentication, has rate limits, or what format the output takes. For a tool with zero annotation coverage, this is a significant gap in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence ('获取海龟汤游戏的玩法') that directly states the tool's purpose with zero wasted words. It's appropriately sized for a simple, no-parameter tool and is front-loaded with the essential information. Every part of the description earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (0 parameters, no annotations, no output schema), the description is minimal but adequate for basic understanding. However, it lacks context about what '海龟汤游戏' (turtle soup game) entails, how the gameplay information is structured, or any behavioral details. For a tool that might return complex instructions, more completeness would be helpful, but the low complexity keeps it from being a 1.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters, and the schema description coverage is 100% (since there are no parameters to describe). The description doesn't need to add parameter semantics, so it meets the baseline expectation. No parameters means no additional burden for the description to compensate, justifying a score of 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose as '获取海龟汤游戏的玩法' (Get the gameplay of the turtle soup game), which is a specific verb ('获取' - get) and resource ('海龟汤游戏的玩法' - gameplay of turtle soup game). It distinguishes from sibling tools like 'get_puzzle' and 'list_puzzles_tool' by focusing on gameplay instructions rather than puzzles themselves. However, it doesn't explicitly contrast with siblings, keeping it at a 4 rather than a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'get_puzzle' or 'list_puzzles_tool'. It doesn't specify whether this is for learning game rules before playing, troubleshooting, or other contexts. There's no mention of prerequisites, exclusions, or comparative use cases, leaving the agent to infer usage from the purpose alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_puzzleC

获取一个谜题的完整内容

    Args:
        puzzle_title: 海龟汤的标题

    Returns:
        选择结果信息
ParametersJSON Schema
NameRequiredDescriptionDefault
puzzle_titleYes

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool retrieves puzzle content but doesn't describe traits like whether it's read-only, requires authentication, has rate limits, or what happens on errors. For a tool with zero annotation coverage, this leaves significant gaps in understanding its behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured, with a clear purpose statement followed by Args and Returns sections. It avoids unnecessary details, though the return description '选择结果信息' (selection result information) is vague. Overall, it's efficient but could be more informative in key areas.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (1 parameter, no annotations, no output schema), the description is incomplete. It lacks details on behavioral traits, usage context, and return values. The vague return description and absence of output schema leave the agent uncertain about what to expect, making it inadequate for effective tool invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds minimal semantics beyond the input schema. It mentions 'puzzle_title: 海龟汤的标题' (puzzle_title: the title of the puzzle), which clarifies the parameter's purpose but doesn't provide format details or examples. With 0% schema description coverage, this offers some compensation but is insufficient for full understanding, aligning with the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: '获取一个谜题的完整内容' (get the complete content of a puzzle). It specifies the verb '获取' (get) and resource '谜题' (puzzle), making the function unambiguous. However, it doesn't explicitly differentiate from sibling tools like 'list_puzzles_tool', which might list puzzles rather than retrieve full content.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'get_prompt' or 'list_puzzles_tool', nor does it specify prerequisites or exclusions. Usage is implied by the purpose but lacks explicit context for selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_puzzles_toolC

列出所有可用的谜题

    Returns:
        谜题列表
ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It states the tool returns a puzzle list, which implies a read-only operation, but doesn't disclose behavioral traits like whether it requires authentication, has rate limits, pagination, or error conditions. This is a significant gap for a tool with no annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is brief with two lines: one stating the purpose and another indicating the return value. However, the 'Returns:' section is somewhat redundant since it just restates '谜题列表' (puzzle list) without adding value. It could be more front-loaded and eliminate the unnecessary return annotation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations and no output schema, the description is incomplete. It doesn't explain the return format (e.g., structure of the puzzle list), error handling, or any behavioral context. For a list operation, this leaves gaps in understanding how to interpret results or handle edge cases.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters with 100% schema description coverage, so the schema fully documents the lack of inputs. The description doesn't need to add parameter details, and it correctly doesn't mention any. Baseline is 4 for zero parameters, as it appropriately avoids redundant information.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: '列出所有可用的谜题' (List all available puzzles). It uses a specific verb ('列出' - list) and resource ('谜题' - puzzles). However, it doesn't differentiate from sibling tools like 'get_puzzle' which likely retrieves a specific puzzle, so it doesn't fully distinguish from alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'get_puzzle' or 'get_prompt'. There's no mention of context, prerequisites, or exclusions. The agent must infer usage from the tool name and description alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 3 tool updatesv1.0.0
    • First observedget_prompt
    • First observedget_puzzle
    • First observedlist_puzzles_tool
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.3/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: get_prompt explains game rules, get_puzzle retrieves a specific puzzle's content, and list_puzzles_tool shows all available puzzles. There is no overlap or ambiguity between these three functions.

Naming Consistency4/5

Two tools follow a consistent verb_noun pattern (get_prompt, get_puzzle), but list_puzzles_tool deviates by adding '_tool' suffix unnecessarily. The naming is still readable and mostly predictable.

Tool Count4/5

Three tools is appropriate for a simple puzzle game server, though slightly minimal. It covers core needs: understanding the game, browsing puzzles, and accessing content. One more tool for puzzle management might enhance completeness.

Completeness3/5

The tools cover basic puzzle retrieval and listing, but lack puzzle creation, updating, or deletion operations. For a game server, this is a notable gap, as agents cannot modify or add puzzles, limiting interactive use.

Maintenance

ActivityInactive
ResponsivenessSyncing

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

Related MCP Servers

  • mcp-dice

    yamaton
    A
    license
    A
    quality
    D
    maintenance
    A MCP server enabling LLMs to roll dice
    1
    4
    MIT

  • DMCP

    shawnrushefsky
    A
    license
    Not graded
    quality
    C
    maintenance
    An MCP server that enables AI agents to act as dynamic dungeon masters for text-based RPGs with dynamically generated rule systems and comprehensive game state management.
    17
    9
    MIT

  • mcp-turtle-noir

    Yuikij
    A
    license
    A
    quality
    B
    maintenance
    MCP server for Turtle Soup lateral thinking puzzles. It enables starting puzzle sessions, asking questions, and revealing solutions via a thin layer over Turtle Noir backend APIs.
    3
    77
    1
    MIT

Appeared in Searches

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/wangyafu/haiguitangmcp'

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