Pokemon Champions Battle Assistant

Pokemon Champions Battle Assistant

Enables live battle statistics queries and precise damage calculations for Pokemon Champions, supporting Japanese and English names, multiple formats, and environmental factors.

Category
访问服务器

README

Pokemon Champions Battle Assistant - MCP Server

This project is a Model Context Protocol (MCP) server for the Pokemon Champions Battle Assistant, built using @hono/mcp and the @modelcontextprotocol/sdk.

It allows LLMs (like Claude) to query live battle statistics and perform damage calculations directly on your local system or remote host.


🛠 Setup & Installation

1. Requirements

  • Node.js v20+
  • The repository [PokemonChampions_Battle-assistant-tool](file:///home/mekabu0551/poke-api-poc/PokemonChampions_Battle-assistant-tool) cloned and populated with databases.

2. Install dependencies

In the root directory, run:

npm install

3. Build & Start the Server

To compile the TypeScript code and start the Hono server:

# Start in development mode (with hot-reloading)
npm run dev

# Or build and run the production server
npm run build
npm start

The server will start listening on http://localhost:8787.


🔌 Connecting to an MCP Client (e.g., Claude Desktop)

To connect Claude Desktop to your local Hono MCP server, add the following configuration to your claude_desktop_config.json:

{
  "mcpServers": {
    "pokemon-champions": {
      "url": "http://localhost:8787/mcp"
    }
  }
}

🧰 Available Tools

Once connected, the following tools will be made available to your LLM:

1. get_pokemon_metadata

  • Description: Returns base stats, types, English name, and ID of a given Pokemon.
  • Parameters:
    • pokemon_name (string, required): Japanese or English name of the Pokemon (e.g., "ガブリアス", "garchomp").

2. get_battle_statistics

  • Description: Returns popularity statistics of moves, items, natures, ev spreads, and abilities for a specific Pokemon in the current environment.
  • Parameters:
    • pokemon_name (string, required)
    • format ("Singles" | "Doubles", default: "Doubles")
    • season (string, optional)

3. calculate_damage

  • Description: Performs a precise Level 50 damage calculation between two Pokemon, factoring in nature, stats, items (like こだわりハチマキ, とつげきチョッキ), ranks, weather, and terrain.
  • Parameters:
    • attacker (object, required): Attacker details (name, evs, nature, ranks, item, teratype).
    • defender (object, required): Defender details (name, evs, nature, ranks, item, teratype).
    • move (string, required): Move name (e.g., "じしん").
    • environment (object, optional): Weather and Terrain settings.

📁 Key Code Files

  • [package.json](file:///home/mekabu0551/poke-api-poc/package.json) — Project configuration and dependencies.
  • [tsconfig.json](file:///home/mekabu0551/poke-api-poc/tsconfig.json) — TypeScript settings.
  • [src/index.ts](file:///home/mekabu0551/poke-api-poc/src/index.ts) — The MCP server implementation.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选