使用说明
用法
结构如下：
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
要使用此服务器，您需要：
安装所需的依赖项：
[如果尚未安装]https://docs.astral.sh/uv/
uv venv
source .venv/bin/activate
uv sync
请参阅.env.example文件，通过添加适当的变量来配置Redis连接。
运行服务器：
python src/server.py
此服务器的功能
资源：
- redis://status-当前连接状态
- redis://infoRedis服务器信息
- redis://keys/{pattern}-列出与模式匹配的键
工具：
- 基本操作：
- get_value-获取一个值
- set_value-设置一个具有可选到期时间的值
- delete_key-删除密钥
- increment-递增一个数值
- 列表操作：
- list_push-将值推送到列表
- list_range-获取列表值的范围
- 哈希运算：
- hash_set-设置哈希字段
- hash_get-获取哈希字段
- 设置操作：
- set_add-添加到集合
- set_members-获取集合成员
- 发布/订阅：
- publish_message-发布消息
每个工具都包括错误处理并返回有意义的响应。如果连接丢失，服务器将自动重新连接到Redis。
您可以使用MCP检查器进行测试：
mcp dev src/server.py
或者在Claude Desktop中安装它：
mcp install src/server.py
示例
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.
此实现为通过MCP集成Redis提供了坚实的基础。您可以根据特定用例的需要添加更多Redis命令来进一步扩展它。