Redis MCP server

The Redis MCP Server is a natural language interface that allows AI agents to interact with Redis databases. It enables storing, retrieving, and managing data in Redis through conversational commands, making it easy to implement Redis operations in AI-driven workflows without writing complex code.

Installation

To install the Redis MCP Server:

# Clone the repository
git clone https://github.com/redis/mcp-redis.git
cd mcp-redis

# Install dependencies using uv
uv venv
source .venv/bin/activate
uv sync

Configuration

The server can be configured using the following environment variables:

Available Tools

The MCP Server provides various tools for Redis operations:

• String tools: Set and get strings with expiration
• Hash tools: Store field-value pairs within a single key
• List tools: Common operations to append and pop items
• Set tools: Add, remove and list set members
• Sorted set tools: Manage score-based data
• Pub/Sub functionality: Publish messages to channels and subscribe
• Streams tools: Add, read, and delete from data streams
• JSON tools: Store, retrieve, and manipulate JSON documents
• Query engine tools: Manage vector indexes and perform vector search
• Server management tool: Retrieve database information

Running the Server

Standard Mode (stdio)

By default, the server runs locally and communicates via stdin/stdout:

uv run src/main.py

Network Mode (SSE)

To make the server available over the network:

export MCP_TRANSPORT="sse"
uv run src/main.py

Test the server:

curl -i http://127.0.0.1:8000/sse

Integration Options

With OpenAI Agents SDK

# Install the Python SDK
pip install openai-agents

# Configure the OpenAI token
export OPENAI_API_KEY="<openai_token>"

# Run the example application
python3.13 redis_assistant.py

With Claude Desktop

Via Smithery (Automatic Configuration)

npx -y @smithery/cli install @redis/mcp-redis --client claude

Manual Configuration

Edit the claude_desktop_config.json configuration file:

{
    "mcpServers": {
        "redis": {
            "command": "<full_path_uv_command>",
            "args": [
                "--directory",
                "<your_mcp_server_directory>",
                "run",
                "src/main.py"
            ],
            "env": {
                "REDIS_HOST": "<your_redis_database_hostname>",
                "REDIS_PORT": "<your_redis_database_port>",
                "REDIS_PWD": "<your_redis_database_password>",
                "REDIS_SSL": true,
                "REDIS_CA_PATH": "<your_redis_ca_path>",
                "REDIS_CLUSTER_MODE": false
            }
        }
    }
}

With Docker

You can use the official Redis MCP Docker image or build your own:

# Build your own image
docker build -t mcp-redis .

To configure Claude Desktop with Docker, add to claude_desktop_config.json:

{
  "mcpServers": {
    "redis": {
      "command": "docker",
      "args": ["run",
                "--rm",
                "--name",
                "redis-mcp-server",
                "-i",
                "-e", "REDIS_HOST=<redis_hostname>",
                "-e", "REDIS_PORT=<redis_port>",
                "-e", "REDIS_USERNAME=<redis_username>",
                "-e", "REDIS_PWD=<redis_password>",
                "mcp/redis"]
    }
  }
}

With VS Code

1. Enable agent mode in settings.json:

{
  "chat.agent.enabled": true
}

2. Add the Redis MCP Server configuration to .vscode/mcp.json or settings.json:

{
  "servers": {
    "redis": {
      "type": "stdio",
      "command": "<full_path_uv_command>",
      "args": [
        "--directory",
        "<your_mcp_server_directory>",
        "run",
        "src/main.py"
      ],
      "env": {
        "REDIS_HOST": "<your_redis_database_hostname>",
        "REDIS_PORT": "<your_redis_database_port>",
        "REDIS_USERNAME": "<your_redis_database_username>",
        "REDIS_PWD": "<your_redis_database_password>"
      }
    }
  }
}

Troubleshooting

For Claude Desktop integration issues, check the log file:

tail -f ~/Library/Logs/Claude/mcp-server-redis.log

You can also use the MCP Inspector for visual debugging:

npx @modelcontextprotocol/inspector uv run src/main.py

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.