Skip to main content
Glama
igs-pochenkuo

SouthAsia MCP Tool

by igs-pochenkuo
OverviewSchemaRelated ServersScoreDiscussions
Python

SouthAsia MCP 工具

License: MIT

歡迎使用 SouthAsia MCP 工具專案！這是一個基於 MCP (Model Control Protocol)-like 框架的工具集，旨在擴充 AI 助理（例如 Cursor）的功能，使其能夠執行更複雜、更貼近本地開發環境的任務。

這個儲存庫可以作為您開發自訂 MCP 工具的模板和起點。

✨ 功能特色

目前包含以下範例工具 (在 hello_world handler 中)：

  • mcp_hello_world: 一個簡單的工具，返回固定的問候語。

  • mcp_hello_name: 接收一個 name 參數，並返回包含該名字的問候語。

您可以輕易地擴充此專案，加入更多實用的工具！

Related MCP server: MCP Server Template for Cursor IDE

🚀 開始使用

1. 環境準備

  • Git: 用於克隆儲存庫。

  • Python: 版本需 >= 3.10。

  • (推薦) uv: 一個快速的 Python 套件安裝與管理工具 (安裝指南)。如果沒有 uv，也可以使用 Python 內建的 venv 和 pip。

2. 安裝步驟

# 1. 克隆儲存庫
git clone <您的儲存庫 URL>
cd southAsia_Tool # 進入專案目錄

# 2. 建立並啟用虛擬環境
# 使用 uv (推薦)
uv venv
source .venv/bin/activate  # Linux/macOS
# 或者 .\.venv\Scripts\Activate.ps1  # Windows PowerShell
# 或者 .\.venv\Scripts\activate.bat # Windows Cmd

# 使用 Python 內建 venv
# python -m venv .venv
# source .venv/bin/activate  # Linux/macOS
# 或者 .\.venv\Scripts\Activate.ps1  # Windows PowerShell
# 或者 .\.venv\Scripts\activate.bat # Windows Cmd

# 3. 安裝依賴
# 使用 uv (推薦)
uv pip sync pyproject.toml

# 4. 使用 pip 編譯工具
pip install -e .

3. 設定 Cursor MCP 工具

  1. 找到 Cursor 設定檔:

    • 通常位於使用者家目錄下的 .cursor 資料夾中。

    • Windows: %USERPROFILE%\.cursor\mcp.json

    • macOS/Linux: ~/.cursor/mcp.json

  2. 編輯 mcp.json:

    • 如果檔案不存在，請建立它。

    • 加入以下內容 (如果已有其他工具，請確保 JSON 格式正確)：

    {
  "southAsia": {
    "command": "cmd", // 或 "bash", "zsh" 等，依您的系統
    "args": [
      "/c", // Windows cmd 的參數，bash/zsh 通常不需要
      "southasia" // 對應 pyproject.toml 中定義的命令名稱
    ]
  }
}

    • 重要:

      • "southAsia": 這是你在 Cursor 中 @ 後面輸入的工具名稱，必須與 server.py 中的 MCP_TOOL_NAME (或您修改後的名稱) 大小寫一致。

      • "southasia": 這是您在步驟 2 安裝後可在終端運行的命令，對應 pyproject.toml 中 [project.scripts] 的設定 (建議小寫)。

      • command 和 args: 請根據您的作業系統和 Shell 調整。Windows PowerShell 可能需要不同的參數。

  3. 重啟 Cursor: 關閉並重新開啟 Cursor 以載入新的 MCP 工具設定。

4. 測試安裝

在 Cursor 的聊天視窗中輸入：

@southAsia mcp_hello_world

如果看到類似 "Hello World! 這是您的第一個 SouthAsia 工具！" 的回應，表示安裝和設定成功！

您也可以測試帶參數的工具：

@southAsia mcp_hello_name name="工程師"

🔧 使用方法

在 Cursor 中，您可以透過 @<工具集名稱> (預設是 @southAsia) 來呼叫此 MCP 工具提供的功能。

  • 基本語法: @<工具集名稱> <工具名稱> [參數]

  • 範例:

    • @southAsia mcp_hello_world

    • @southAsia mcp_hello_name name="您的名字"

當您加入更多工具後，可以用同樣的方式呼叫它們。

💻 開發新工具

想要擴充這個工具集嗎？

  1. 主要結構:

    • src/southasia/handlers/: 存放工具處理邏輯的 Python 檔案。每個檔案可以包含一組相關的工具。

    • src/southasia/server.py: MCP 伺服器的主要設定檔，您需要在此處註冊新的 Handler。

  2. 開發指南:

    • 我們為您準備了詳細的開發指南！在 Cursor 中，當您編輯 src/southasia/handlers/ 目錄下的 Python 檔案時，會自動載入 @100-Lang-PythonMCPHandlerGuide.mdc 規則，其中包含了建立新工具的步驟和建議。

    • 您也可以直接在 Cursor 中 @100-Lang-PythonMCPHandlerGuide.mdc 來查閱。

  3. 基本步驟:

    • 在 handlers 目錄下建立新的 .py 檔案 (例如 my_tools.py)。

    • 在檔案中實作 handle_list_tools (定義工具) 和 handle_call_tool (處理呼叫) 函數。

    • 在 server.py 中導入您的 Handler 並將其加入 HANDLERS 列表。

✏️ 重新命名專案

如果您不想使用 "southAsia" 這個名稱，可以將整個專案重新命名。這是一個比較進階的操作，涉及修改多個檔案和設定。

詳細步驟請參考專案內的 MDC 規則：在 Cursor 中 @010-Core-ProjectRenamingGuide.mdc。

❓ 故障排除提示

如果在安裝、設定或使用過程中遇到問題，可以嘗試以下步驟：

  • 確認虛擬環境: 確保你已經在專案的虛擬環境中執行安裝和運行命令。

  • 檢查 Cursor 設定 (mcp.json):

    • 仔細核對工具集名稱 (例如 "southAsia") 是否與 server.py 中的 MCP_TOOL_NAME 大小寫完全一致。

    • 確認 args 中的命令行工具名稱 (例如 "southasia") 是否與 pyproject.toml 中 [project.scripts] 定義的大小寫完全一致。

    • 檢查 command 和 args 是否適合你的作業系統和 Shell 環境。

  • 手動運行服務器: 在已啟用虛擬環境的終端中，直接運行 southasia (或你修改後的命令)。觀察是否有任何錯誤訊息或日誌輸出。這有助於判斷 MCP 服務本身是否能正常啟動。

  • 檢查 Cursor 輸出: 查看 Cursor 的「輸出」(Output) 面板，有時 MCP 相關的錯誤會顯示在那裡。

  • 重啟 Cursor: 在修改 mcp.json 或重新安裝後，重啟 Cursor。

📄 授權條款

本專案採用 MIT 授權條款。

Available Tools

2 tools
mcp_hello_nameB

A demonstration tool that greets you by name

ParametersJSON Schema
NameRequiredDescriptionDefault
nameYesYour name

TDQS

B3.1/5.0
Behavior2/5

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

No annotations are provided, so the description carries full burden. It states the tool 'greets you by name' but doesn't disclose behavioral traits like whether this is a read-only operation, what format the greeting returns, if there are any side effects, or authentication requirements. The description is minimal and lacks behavioral context.

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, efficient sentence that clearly states the tool's purpose. It's appropriately sized for a simple greeting tool with one parameter. Every word earns its place with zero waste or redundancy.

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

Completeness3/5

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

For a simple greeting tool with one parameter and no output schema, the description is adequate but has clear gaps. It explains what the tool does but doesn't provide usage context, behavioral details, or output information. Given the tool's simplicity, the description meets minimum viable standards but could be more complete.

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?

Schema description coverage is 100% with the single parameter 'name' well-documented as 'Your name'. The description adds no additional parameter semantics beyond what the schema provides. With high schema coverage, the baseline score of 3 is appropriate as the schema does the heavy lifting.

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: 'greets you by name' specifies the action (greeting) and resource (name). It distinguishes from sibling 'mcp_hello_world' by specifying personalized greeting vs generic greeting. However, it doesn't explicitly mention the sibling differentiation in the description text itself.

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. There's no mention of sibling tool 'mcp_hello_world' or any context about when a personalized greeting is preferred over a generic one. The description simply states what it does without usage context.

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

mcp_hello_worldB

A simple demonstration tool that returns a greeting message

ParametersJSON Schema
NameRequiredDescriptionDefault
random_stringYesDummy parameter for no-parameter tools

TDQS

B3.1/5.0
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 greeting message', implying a read-only operation, but doesn't disclose any behavioral traits like error handling, rate limits, or authentication needs. For a tool with no 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, efficient sentence: 'A simple demonstration tool that returns a greeting message'. It is front-loaded with the core purpose and wastes no words, making it appropriately sized and easy to parse.

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

Completeness3/5

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

Given the tool's simplicity (one parameter with full schema coverage, no output schema), the description is adequate but has clear gaps. It explains the basic purpose but lacks usage guidelines and behavioral details, making it minimally viable but not fully complete for effective agent use.

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 input schema has 100% description coverage, with the parameter 'random_string' documented as a 'Dummy parameter for no-parameter tools'. The description adds no additional parameter semantics beyond this, so it meets the baseline of 3 where the schema does the heavy lifting without extra value from the description.

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: 'returns a greeting message' with 'simple demonstration' providing context. It specifies the verb 'returns' and resource 'greeting message', making it understandable. However, it doesn't explicitly differentiate from its sibling 'mcp_hello_name', which appears similar, keeping it from a perfect score.

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 mentions 'simple demonstration' but doesn't specify contexts, exclusions, or compare to 'mcp_hello_name'. This lack of usage instructions leaves the agent without clear direction for tool selection.

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. 2 tool updates
    • First observedmcp_hello_name
    • First observedmcp_hello_world
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.2/5.0
Disambiguation4/5

The two tools have distinct purposes: one greets by name and the other returns a generic greeting. While both involve greetings, the specific functionality differs enough to avoid confusion, though the overlap in greeting theme could cause minor ambiguity if not carefully read.

Naming Consistency5/5

Both tools follow a consistent naming pattern with 'mcp_' prefix and descriptive suffixes ('hello_name' and 'hello_world'). This uniformity makes it easy to predict and understand the tool set's structure.

Tool Count2/5

With only 2 tools, the server feels under-scoped for a general-purpose MCP server, as it lacks coverage for typical operations beyond basic greetings. This minimal count suggests limited utility for complex agent tasks.

Completeness2/5

Inferred as a demonstration or greeting server, the tool set is severely incomplete—it only offers greeting functions without any CRUD, data manipulation, or broader utility operations. This leaves obvious gaps for practical agent workflows.

Maintenance

ActivityInactive
ResponsivenessNo issues

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

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/igs-pochenkuo/southasia_mcp'

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