About mcp-pokeapi-server
mcp-pokeapi-server uses POKEAPI to retrieve Pokémon information by name or ID for MCP clients and LLM applications. It communicates through JSON-RPC 2.0 over stdio and validates inputs with zod.
Key features
- 01Look up Pokémon by name or ID
- 02Communicate via JSON-RPC 2.0 over stdio
- 03Validate inputs with zod
Use cases
- 01Query Pokémon details from an MCP client
- 02Retrieve information by name or ID in an LLM app
MCP support
The MCP server exposes a getPokemonInfo tool to clients, accepts JSON-RPC requests over stdio, and fetches information from POKEAPI.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEmcp-pokeapi-server
POKEAPI と連携し、MCP(Model Context Protocol)仕様でポケモン情報を取得できるサーバーです。
概要
- MCP プロトコル(JSON-RPC 2.0 over stdio)で、LLM アプリや MCP クライアントからポケモン情報取得ツールを提供します。
- POKEAPI(https://pokeapi.co/)を利用。
- スキーマバリデーションにはzodを使用。
セットアップ
npm install
ビルド
npx tsc
開発用起動(ts-node)
npx ts-node src/index.ts
MCP クライアントからの利用例
MCP クライアントや LLM アプリから、標準入力/出力で JSON-RPC リクエストを送信します。
1. ツール一覧取得(list_tools)
{
"jsonrpc": "2.0",
"id": 1,
"method": "list_tools"
}
レスポンス例
{
"jsonrpc": "2.0",
"id": 1,
"result": {
"tools": [
{
"name": "getPokemonInfo",
"description": "ポケモン名またはIDから、POKEAPIでポケモン情報を取得します。",
"input_schema": { ... },
"output_schema": { ... }
}
]
}
}
2. ポケモン情報取得(call_tool)
{
"jsonrpc": "2.0",
"id": 2,
"method": "call_tool",
"params": {
"name": "getPokemonInfo",
"arguments": {
"nameOrId": "pikachu"
}
}
}
レスポンス例
{
"jsonrpc": "2.0",
"id": 2,
"result": {
"content": [
{
"type": "json",
"data": {
"name": "pikachu",
"id": 25,
"height": 4,
"weight": 60,
"types": ["electric"]
}
}
]
}
}
テスト
npm test
参考
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.