Pokemon MCP Server
An MCP server that provides standardized access to Pokemon data, allowing users to search, compare, and retrieve detailed information about Pokemon through natural language tools.
README
Pokemon MCP Server
A Model Context Protocol (MCP) server that provides Pokemon data through standardized tools. This monorepo contains both the MCP server and data ingestion service for fetching Pokemon data from PokeAPI.
Architecture
This is a PNPM monorepo with two main packages:
- pokemon-mcp-server: MCP server that exposes Pokemon data through standardized tools
- pokemon-mcp-ingestion: Data ingestion service that fetches from PokeAPI and stores in SQLite
The system uses a shared SQLite database (data/pokemon.sqlite) for Pokemon data storage.
Features
MCP Tools Available
get_pokemon- Get detailed information about a specific Pokemonsearch_pokemon- Search Pokemon by name, type, or other criteriaget_strongest_pokemon- Find the strongest Pokemon by various statsget_pokemon_stats- Get detailed stats for a Pokemoncompare_pokemon- Compare stats between two Pokemonget_type_effectiveness- Get type effectiveness information
Data Coverage
- Complete Pokemon data from PokeAPI
- Stats, types, abilities, and more
- Type effectiveness relationships
- Searchable by multiple criteria
Quick Start
Prerequisites
- Node.js 18+
- PNPM
- Git
Installation
- Clone the repository:
git clone https://github.com/grovesjosephn/pokemcp.git
cd pokemcp
- Install dependencies:
pnpm install
- Set up the database:
./scripts/setup.sh
- Build all packages:
pnpm build
Usage
Running the MCP Server
# Development mode (with hot reload)
pnpm dev
# Production mode
cd packages/pokemon-mcp-server
pnpm start
Testing with MCP Inspector
# Visual GUI testing
cd packages/pokemon-mcp-server
pnpm inspect
# CLI testing
pnpm inspect:cli
Data Ingestion
# Run data ingestion
cd packages/pokemon-mcp-ingestion
pnpm start
Claude Desktop Integration
Option 1: NPM Package (Recommended)
Install the server globally:
cd packages/pokemon-mcp-server
pnpm build
npm link
Configure Claude Desktop:
{
"mcpServers": {
"pokemon": {
"command": "pokemon-mcp-server",
"env": {
"POKEMON_DATA_DIR": "/path/to/pokemcp/data"
}
}
}
}
Option 2: Direct Node Execution
{
"mcpServers": {
"pokemon": {
"command": "node",
"args": ["/path/to/pokemcp/packages/pokemon-mcp-server/dist/server.js"],
"env": {
"POKEMON_DATA_DIR": "/path/to/pokemcp/data"
}
}
}
}
Option 3: Development Mode
{
"mcpServers": {
"pokemon": {
"command": "pnpm",
"args": ["--filter", "pokemon-mcp-server", "start"],
"cwd": "/path/to/pokemcp",
"env": {
"POKEMON_DATA_DIR": "/path/to/pokemcp/data"
}
}
}
}
Development
Workspace Commands
pnpm build # Build all packages
pnpm dev # Run all packages in development mode
pnpm test # Run tests for all packages
pnpm lint # Lint all packages
pnpm format # Format all files
pnpm format:check # Check formatting
Server Package Commands
cd packages/pokemon-mcp-server
pnpm build # Compile TypeScript
pnpm dev # Watch mode with tsx
pnpm start # Run server
pnpm inspect # Run MCP Inspector GUI
pnpm inspect:cli # Run MCP Inspector CLI
pnpm test # Run tests
Ingestion Package Commands
cd packages/pokemon-mcp-ingestion
pnpm build # Compile TypeScript
pnpm dev # Watch mode
pnpm start # Run ingestion
pnpm test # Run tests
Testing
The project uses Vitest for testing:
# Run all tests
pnpm test
# Run specific package tests
pnpm --filter pokemon-mcp-server test
pnpm --filter pokemon-mcp-ingestion test
Database Schema
The SQLite database includes tables for:
pokemon- Basic Pokemon informationstats- Pokemon stats (HP, Attack, Defense, etc.)types- Pokemon types and relationshipsabilities- Pokemon abilitiestype_effectiveness- Type effectiveness relationships
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests
- Run
pnpm formatandpnpm lint - Submit a pull request
Commit Guidelines
Use conventional commit format:
<type>[optional scope]: <description>
Examples:
- feat(server): add Pokemon evolution chain tool
- fix(ingestion): handle missing species URL gracefully
- docs: update integration guide
License
MIT License - see LICENSE file for details
Links
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。