About Redis MCP Server
Redis MCP Server is a Python MCP server packaged for Docker. It exposes basic Redis key operations and includes persistence, health checks, logging, and environment-based configuration.
Key features
- 01Set, get, and delete Redis keys
- 02List keys by pattern
- 03Redis persistence
- 04Docker and Docker Compose support
- 05Health checks and error logging
- 06Environment-based configuration
Use cases
- 01Read or update Redis values through an MCP client
- 02Find keys matching a pattern
- 03Run a Redis and MCP setup with Docker
MCP support
Exposes Redis operations to MCP clients, including setting, retrieving, deleting, and listing keys.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMERedis MCP Server
A professional implementation of a Redis server with MCP (Model Control Protocol) integration, containerized with Docker.
Features
- Redis server with persistence
- MCP server integration for Redis operations
- Docker and Docker Compose support
- Comprehensive error handling and logging
- Environment-based configuration
- Health checks for Redis service
Prerequisites
- Docker
- Docker Compose
Quick Start
- Clone the repository:
git clone https://github.com/cbuitragoh/customRedis.git
cd customredis
- Start the services:
docker-compose up -d
- Check the logs:
docker-compose logs -f
Available Redis Operations
The MCP server provides the following Redis operations:
set_redis_key(key: str, value: str): Set a key-value pairget_redis_key(key: str): Retrieve a value by keydelete_redis_key(key: str): Delete a keylist_redis_keys(pattern: str = '*'): List all keys matching a pattern
Configuration
The application can be configured through environment variables:
REDIS_HOST: Redis server host (default: redis)REDIS_PORT: Redis server port (default: 6379)REDIS_DB: Redis database number (default: 0)LOG_LEVEL: Logging level (default: INFO)
Development
Local Development
- Create a virtual environment:
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
- Install dependencies:
pip install -r requirements.txt
- Run the server:
python src/server.py
Docker Development
- Build the image:
docker-compose build
- Run the services:
docker-compose up
Project Structure
.
├── src/
│ └── server.py # Main server implementation
├── Dockerfile # Docker configuration
├── docker-compose.yml # Docker Compose configuration
├── requirements.txt # Python dependencies
├── .env # Environment variables
└── README.md # This file
Error Handling
The application includes comprehensive error handling:
- Connection errors
- Redis operation errors
- Server startup/shutdown errors
- Graceful shutdown on keyboard interrupt
Logging
The application uses Python's logging module with the following features:
- Timestamp-based log entries
- Different log levels (INFO, WARNING, ERROR)
- Detailed error messages
- Operation success/failure logging
Using with Claude Desktop
To use this Redis MCP server with Claude Desktop, add the following configuration to your Claude Desktop settings:
{
"mcpServers": {
"redis": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--network",
"customredis_redis-network",
"customredis-mcp-server"]
}
}
}
This configuration:
- Uses Docker to run the Redis MCP server
- Connects to Redis using the host machine's Redis instance
- Runs in interactive mode (-i)
- Removes the container after use (--rm)
- Connect the MCP server to same network to Redis container
Make sure:
- Redis is running in container from docker-compose redis service
- The Redis port (6379) is accessible
- Docker is running on your system
License
MIT License
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.