The Redis MCP Server provides a natural language interface for agentic applications to manage and query data within Redis. It enables AI-driven workflows to interact with structured and unstructured data, offering efficient data manipulation and retrieval for developers building AI assistants, chatbots, and data analytics tools.

How It Works

This server acts as a bridge between AI models and Redis, translating natural language commands into Redis operations via the Model Content Protocol (MCP). It supports a wide array of Redis data structures, including strings, hashes, lists, sets, sorted sets, streams, and JSON, along with tools for vector indexing and search. The architecture leverages uvx for streamlined server deployment and execution, facilitating seamless integration with various MCP clients.

Quick Start & Requirements

• Installation: Available via PyPI (pip install redis-mcp-server) or directly from GitHub. Docker images are also provided.
• Primary Command (PyPI): uv run redis-mcp-server --url redis://localhost:6379/0 (after pip install and uv sync).
• Primary Command (GitHub): uvx --from git+https://github.com/redis/mcp-redis.git@<tag> redis-mcp-server --url redis://localhost:6379/0.
• Prerequisites: Requires a running Redis instance. The uv package manager is heavily utilized for managing environments and running the server.
• Configuration: Supports configuration via command-line arguments or environment variables (e.g., REDIS_HOST, REDIS_PORT, REDIS_PWD).
• Documentation: The project's README serves as the primary documentation.

Highlighted Details

• Natural Language Interface: Empowers AI agents to query, store, index, and search Redis data using natural language.
• Comprehensive Redis Support: Manages all standard Redis data types, including advanced features like vector embeddings and stream consumer groups.
• Key Integrations: Designed for seamless integration with frameworks like OpenAI Agents SDK, and tools such as Claude Desktop, VS Code with GitHub Copilot, and Augment.
• Vector Search: Includes dedicated tools for managing vector indexes and performing similarity searches.

Maintenance & Community

The project is actively developed, with the main branch potentially containing breaking changes. Support and questions are primarily handled through GitHub Issues.

Licensing & Compatibility

Licensed under the permissive MIT License, allowing for broad compatibility with commercial and closed-source applications.

Limitations & Caveats

The streameable.http transport is planned for future support but is not currently available. Users should exercise caution when using the main development branch due to potential instability.