Redis MCP Server

What does “Redis” MCP Server do?

The Redis MCP Server is a Model Context Protocol (MCP) server designed to facilitate seamless interaction between AI assistants and Redis-compatible in-memory databases such as Redis Server and AWS Memory DB. Acting as a bridge, it allows AI-driven workflows to perform key-value storage operations, manage cached data, and execute a variety of database tasks programmatically. By exposing resources and tools through standardized MCP endpoints, the Redis MCP Server enables tasks such as querying the database, managing lists, hashes, and sets, and even real-time Pub/Sub messaging. This empowers developers and AI agents to integrate fast, scalable in-memory storage and retrieval into their applications, boosting performance and enabling advanced automation in development workflows.

List of Prompts

No explicit prompt templates are mentioned in the repository.

List of Resources

• redis://status
  Provides the current connection status to the Redis server, including host, port, and database information.

• redis://info
  Exposes general information about the connected Redis server, such as server version and configuration details.

• redis://keys/{pattern}
  Lists all keys in the Redis database that match a specified pattern, useful for browsing or searching stored data.

List of Tools

• get_value
  Retrieves the value associated with a specific key in the Redis database.
• set_value
  Stores a value under a given key, with optional expiry support.
• delete_key
  Deletes a specified key from the database.
• increment
  Atomically increments the numeric value of a key.
• list_push
  Pushes one or more values to a list data structure.
• list_range
  Retrieves a range of values from a list.
• hash_set
  Sets one or more fields in a hash.
• hash_get
  Retrieves one or more fields from a hash.
• set_add
  Adds one or more members to a set.
• set_members
  Retrieves all members of a set.
• publish_message
  Publishes a message to a specified channel using Redis Pub/Sub.

Use Cases of this MCP Server

• Database Management & Monitoring
  AI agents and developers can monitor the connection status, inspect server info, and manage keys, enabling robust database administration and health checks.

• Dynamic Caching for Applications
  Integrate fast, AI-driven in-memory caching for web and backend applications, allowing temporary storage and retrieval of frequently accessed data.

• Real-time Messaging
  Utilize Pub/Sub capabilities to build real-time chatbots, notification systems, or collaborative environments powered by Redis messaging.

• Workflow Automation
  Automate data ingestion, transformation, and storage operations through MCP tools (lists, hashes, sets), accelerating ETL and AI data pipeline tasks.

• Session & State Management
  Manage user sessions and stateful information for web apps, bots, and microservices via fast key-value operations.

How to set it up

Windsurf

1. Ensure Node.js and Windsurf are installed.
2. Download or clone the repository.
3. Add the Redis MCP Server to your Windsurf configuration.
4. Example JSON configuration:

   {
     "mcpServers": {
       "redis-mcp": {
         "command": "python",
         "args": ["src/server.py"]
       }
     }
   }
   

5. Save the config, restart Windsurf, and check connectivity.

Securing API Keys

Use a .env file modeled after .env.example to store Redis credentials. Reference the environment file in your configuration:

{
  "env": {
    "REDIS_HOST": "yourhost",
    "REDIS_PORT": "6379",
    "REDIS_PASSWORD": "yourpassword"
  }
}

Claude

1. Install Claude Desktop if not present.
2. Download/clone the repository.
3. Open Claude Desktop settings.
4. Add the MCP Server using:

   {
     "mcpServers": {
       "redis-mcp": {
         "command": "python",
         "args": ["src/server.py"]
       }
     }
   }
   

5. Save and restart Claude Desktop.

Cursor

1. Ensure Cursor is installed on your system.
2. Clone the MCP Server repository.
3. In Cursor’s configuration, add the server:

   {
     "mcpServers": {
       "redis-mcp": {
         "command": "python",
         "args": ["src/server.py"]
       }
     }
   }
   

4. Restart Cursor and validate the integration.

Cline

1. Install Cline if not already done.
2. Clone the repository.
3. Open Cline’s configuration file.
4. Insert:

   {
     "mcpServers": {
       "redis-mcp": {
         "command": "python",
         "args": ["src/server.py"]
       }
     }
   }
   

5. Save and restart Cline.

Securing API Keys

In each platform, use environment variables for credentials as shown above.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "redis-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “redis-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Our opinion

The Redis MCP Server is robust and clearly documented, exposing a wide range of Redis functionalities and following MCP conventions for resources and tools. The lack of prompt templates and explicit sampling/roots features lowers the flexibility slightly, but overall utility is high for in-memory key-value use cases.

MCP Score

Rating:
I would rate this MCP server an 8 out of 10. It is well-structured, with solid documentation and a strong set of resources and tools. The absence of prompt templates and explicit mention of advanced features like roots or sampling leaves some gaps for more advanced MCP workflows.