Pokemon MCP Server
Enables users to fetch detailed Pokémon data, build tournament squads, and simulate battles using PokéAPI. It also integrates Wikipedia to provide fun comparisons between Pokémon and their real-world animal inspirations.
README
Pokemon MCP Server
A MCP (Model Context Protocol) server that connects to two APIs — PokéAPI for live Pokémon data and the Wikipedia REST API (free, no key needed) for real-world animal facts — and exposes tools that an LLM (like Claude) can use to fetch, explore, and battle Pokémon.
Built with FastMCP and httpx.
Tools
| Tool | Description |
|---|---|
get_pokemon_info |
Get detailed info (types, abilities, stats) for any Pokémon by name |
list_popular_pokemon |
List popular tournament-ready Pokémon picks |
create_tournament_squad |
Build a powerful 6-Pokémon squad for a tournament |
find_pokemon_by_type |
Find top 5 Pokémon of a given type (e.g. fire, water, psychic) with stats |
battle_simulator |
Simulate a 1v1 battle between two Pokémon based on their stats |
pokemon_real_animal |
Find which real animal a Pokémon resembles, with fun facts pulled from the Wikipedia API |
How pokemon_real_animal Works
For animal data, the tool uses the Wikipedia API (free, no API key needed) to pull real-world animal facts. Here's how it works:
- Uses a hardcoded mapping of Pokémon → real animal (e.g. Pikachu → Mouse, Garchomp → Hammerhead Shark)
- Hits Wikipedia's REST API to fetch a summary about that animal
- Returns a fun comparison alongside the Pokémon's stats
Covers 60+ Pokémon with known real-world inspirations.
Requirements
- Python 3.8+
httpxmcp(Model Context Protocol library)
Installation
# Clone the repo
git clone https://github.com/your-username/pokemon-mcp-server
cd pokemon-mcp-server
# Create a virtual environment
python -m venv venv
.\venv\Scripts\Activate # On Windows
# source venv/bin/activate # On macOS/Linux
# Install dependencies
pip install httpx "mcp[cli]"
Running the Server
python poke.py
The server runs over stdio transport, making it compatible with Claude Desktop and other MCP-compatible LLM hosts.
Connect to Claude Desktop
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"pokemon": {
"command": "python",
"args": ["/path/to/poke.py"]
}
}
}
Example Interactions
- "What are Charizard's stats?"
- "Find me the top fire type Pokémon"
- "Simulate a battle between Pikachu and Mewtwo"
- "What real animal does Garchomp resemble?"
- "Build me a tournament squad"
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。