広告掲載
MCP.so
ログイン

Poké Battle MCP Server

@shreyahhh

リポジトリ

基本情報

カテゴリ

AI とエージェント

トランスポート

stdio

作者

shreyahhh

Poké Battle MCP Server について

概要はまだありません

Poké Battle MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "Pokemon-Battle-using-MCP-Server-connected-to-Claude": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        ".venv"
      ]
    }
  }
}

Poké Battle MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Poké-Battle?

Poké-Battle is a Pokemon game built with FastAPI and Python, leveraging Anthropic’s Claude AI through a custom Model Context Protocol (MCP) server and client. It features real-time battles and uses AI for creative battle descriptions, attack recommendations, and generating unique personalities for caught Pokemon.

How to use Poké-Battle?

Clone the repository, create and activate a Python virtual environment, then install dependencies. Set your Anthropic API key in a .env file, run the MCP server on port 8000 (uvicorn mcp_server:app --reload --port 8000), then run the main game server on port 8080 (uvicorn server:app --reload --port 8080). Open http://localhost:8080 in your browser to play.

Key features of Poké-Battle

  • Catch random Pokemon to build your team.
  • Turn-based battles against a random opponent Pokemon.
  • AI‑generated battle descriptions via Claude.
  • AI‑suggested attack moves during battle.
  • Each caught Pokemon gets a unique, AI‑generated personality.
  • Real‑time game state and message updates via WebSocket.
  • Demonstrates a Model Context Protocol for AI model interaction.

Use cases of Poké-Battle

  • Play a Pokemon battle game with AI‑driven narratives.
  • Learn how to integrate Anthropic’s Claude into a web game using MCP.
  • Experiment with real‑time WebSocket updates in a FastAPI application.
  • Showcase creative AI text generation for game commentary.

よくある質問

1

What dependencies does Poké-Battle require?

The project requires Python, FastAPI, Uvicorn, Anthropic’s Claude API (via API key), PokeAPI, and libraries such as python-dotenv, httpx, websockets, and Jinja2.

2

How do I set up the Anthropic API key?

Create a `.env` file in the root directory and add `ANTHROPIC_API_KEY=your_api_key_here`. For production, it’s recommended to use environment variables from your hosting environment instead of a `.env` file.

3

Do I need to run two servers?

Yes. The MCP server runs on port 8000 (the AI backend), and the main game server runs on port 8080 (handles game logic and serves the frontend). Both must be running simultaneously.

4

How does Poké-Battle use the MCP?

The MCP server (`mcp_server.py`) handles communication with the Anthropic API. The main server (`server.py`) uses an MCP client (`mcp_client.py`) to send requests to the MCP server, enabling AI features like battle descriptions, attack suggestions, and Pokemon personalities.

5

What transport does Poké-Battle use?

Game state and messages are updated in real time via WebSocket. The MCP communication between servers uses HTTP (FastAPI endpoints).

コメント

「AI とエージェント」の他のコンテンツ

OpenZiti MCP Gateway

openziti

NetFoundry MCP Gateway enables secure, isolated access to Model Context Protocol (MCP) tools across distributed systems without exposing public endpoints. Zero trust gateway for MCP servers. Aggregate, filter, and secure

48

scvd.store

seancrecord

scvd.store is an evidence observatory for agentic commerce. Independent signed observation of what other people's endpoints, artifacts and payments actually did among other things. USDC on Base, Arbitrum One, World Chain

2

strac-mcp-dlp

strac-io

Detect and redact PII, PHI, PCI and secrets — SSNs, credit cards, passports, API keys and cloud credentials — in text and in local files, using the Strac DLP API. Five tools: redact_text, detect_sensitive_data, detect_fi

3

Agentic Atlas

Avery Jones

Consult field-tested agent-system design patterns through 8 hosted, read-only tools for orientation, deep reading, relationships, provenance, glossary terms, and publication decisions.

TruVerifAI Panel-review

TruVerifAI

TruVerifAI's Panel Review is the guardian agent for AI's highest-stakes coding decisions: four frontier models argue over an AI coding agent's riskiest designs, diffs, and commits before they execute, with local review g

1
広告掲載