Mcp Server Redis

What is Mcp Server Redis about?

Mcp Server Redis implements an MCP‑compatible server that wraps common Redis commands into resources (status, info, key listing) and tools (basic CRUD, list, hash, set, and Pub/Sub operations). It is designed for LLMs or other agents to interact with Redis‑based caches, AWS MemoryDB, or any compatible key‑value store without writing custom code.

How to use Mcp Server Redis?

1. Install dependencies – the project uses the uv Python tool. Example:

   uv venv
   source .venv/bin/activate
   uv sync
   

2. Configure connection – copy .env.example to .env and fill in your Redis host, port, password, etc.
3. Run the server – start the MCP server with:

   python src/server.py
   

4. Interact – either via the MCP Inspector (mcp dev src/server.py) or by installing the server in Claude Desktop (mcp install src/server.py).

Key Features

• Resources: redis://status, redis://info, redis://keys/{pattern}
• Basic Tools: get_value, set_value (with expiry), delete_key, increment
• List Tools: list_push, list_range
• Hash Tools: hash_set, hash_get
• Set Tools: set_add, set_members
• Pub/Sub Tool: publish_message
• Automatic reconnection on connection loss
• Structured error handling with clear responses

Use Cases

• Caching layer for web services where LLMs need fast read/write access
• Session storage for conversational agents
• Feature flag or configuration store accessed by AI workflows
• Real‑time notifications using Redis Pub/Sub for event‑driven LLM actions
• Data enrichment where agents pull auxiliary data from Redis hashes or lists

FAQ

Q: Which Redis variants are supported? A: Any Redis‑compatible service, including AWS MemoryDB, Azure Cache for Redis, or a local Redis instance.

Q: Do I need to modify code to add new Redis commands? A: New commands can be added by creating additional tool modules under src/tools/ and exposing them via the MCP server.

Q: How does the server handle connection failures? A: It includes retry logic that automatically reconnects and reports the status through the redis://status resource.

Q: Can I limit which keys are exposed? A: The redis://keys/{pattern} resource lets you query keys by pattern, allowing you to enforce naming conventions.

Q: Is authentication required? A: Provide credentials in the .env file; the server uses them to establish a secure connection to Redis.

Usage

The structure is as follows:

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

To use this server, you'll need to:

Install the required dependencies:

[If not already installed] https://docs.astral.sh/uv/

uv venv

source .venv/bin/activate

uv sync

Refer to the .env.example file to configure your Redis connection by adding the appropriate variables.

Run the server:

python src/server.py

Capabilities of this server

Resources:

• redis://status - Current connection status
• redis://info - Redis server information
• redis://keys/{pattern} - List keys matching a pattern

Tools:

• Basic operations:
  • get_value - Get a value
  • set_value - Set a value with optional expiry
  • delete_key - Delete a key
  • increment - Increment a numeric value
• List operations:
  • list_push - Push values to a list
  • list_range - Get range of list values
• Hash operations:
  • hash_set - Set hash fields
  • hash_get - Get hash fields
• Set operations:
  • set_add - Add to a set
  • set_members - Get set members
• Pub/Sub:
  • publish_message - Publish a message

Each tool includes error handling and returns meaningful responses. The server will automatically reconnect to Redis if the connection is lost.

You can test it with the MCP Inspector: mcp dev src/server.py

Or install it in Claude Desktop: mcp install src/server.py

Example

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.

This implementation provides a solid foundation for Redis integration through MCP. You can extend it further by adding more Redis commands as needed for your specific use case.