使用法
構造は次のとおりです。
mcp-server-redis/
├── src/
│ ├── __init__.py
│ ├── main.py # Main entry point
│ ├── config.py # Configuration
│ ├── connection.py # Redis connection management
│ ├── resources/ # Resource implementations
│ │ ├── __init__.py
│ │ ├── status.py # Connection status resources
│ │ └── keys.py # Key-related resources
│ └── tools/ # Tool implementations
│ ├── __init__.py
│ ├── basic.py # Basic Redis operations
│ ├── lists.py # List operations
│ ├── hashes.py # Hash operations
│ ├── sets.py # Set operations
│ └── pubsub.py # Pub/Sub operations
├── tests/ # Test directory
│ └── __init__.py
├── README.md
└── pyproject.toml
このサーバーを使用するには、次のことが必要です。
必要な依存関係をインストールします。
[まだインストールされていない場合] https://docs.astral.sh/uv/
uv venv
source .venv/bin/activate
uv sync
適切な変数を追加して Redis 接続を構成するには、.env.example ファイルを参照してください。
サーバーを実行します。
python src/server.py
Related MCP server: Code Analysis MCP Server
このサーバーの機能
リソース:
redis://status - 現在の接続ステータス
redis://info - Redis サーバー情報
redis://keys/{pattern} - パターンに一致するキーを一覧表示する
ツール:
基本操作:
リスト操作:
ハッシュ操作:
集合演算:
パブリッシュ/サブスクライブ:
各ツールにはエラー処理機能が搭載されており、意味のあるレスポンスを返します。接続が失われた場合、サーバーは自動的にRedisに再接続します。
MCP Inspector でテストできます: mcp dev src/server.py
または、Claude Desktop にインストールします: mcp install src/server.py
例
User: What's the current Redis connection status?
LLM: Let me check the Redis connection status for you.
[Reading resource redis://status]
The Redis server is currently connected and running on localhost:6379, database 0.
User: Can you store my name "Alice" in Redis?
LLM: I'll help you store your name in Redis using the set_value tool.
[Calling set_value with key="name" value="Alice"]
Successfully set key 'name'
I've stored your name "Alice" in Redis under the key "name". Would you like me to verify the value was stored correctly by retrieving it?
User: Yes please verify it
LLM: I'll retrieve the value using the get_value tool.
[Calling get_value with key="name"]
Alice
Yes, I can confirm that your name "Alice" was successfully stored in Redis and can be retrieved correctly. The value matches exactly what we stored.
この実装は、MCP を介した Redis 統合のための強固な基盤を提供します。特定のユースケースに合わせて、必要に応じて Redis コマンドを追加することで、さらに拡張できます。