About
Redis's official MCP server gives agents a natural-language interface to manage and search data in Redis — read/write keys, work with hashes/lists/sets, run vector and full-text search, ideal as a memory and cache layer for AI apps.
Our Verdict
Redis MCP brings database capabilities to the MCP ecosystem. Its GitHub popularity reflects community trust, and the standardized protocol ensures broad compatibility across AI clients.
Pricing
Use Cases
- Integrating database capabilities into AI agent workflows
- Building custom AI-powered tools with Redis MCP
- Enhancing AI agent functionality with standardized MCP access
Pros
- Redis MCP provides standardized MCP protocol access
- Open source with 555 GitHub stars
- Active development and community support
Cons
- Requires MCP-compatible client (Claude, Cursor, etc.)
- Setup complexity varies by client
- Some features may depend on client capabilities
Installation
uvx --from git+https://github.com/redis/mcp-redis.git redis-mcp-serverFrequently Asked Questions
What is Redis MCP mainly for?
It lets agents operate Redis directly in natural language: get/set keys, manage hashes/lists/sets/sorted sets, set TTLs, and use Redis vector and full-text search. A common use is giving AI apps conversation memory, semantic caching and session-state storage.
How do I install Redis MCP?
It is a Python implementation; the recommended way is a zero-install uvx run: uvx --from git+https://github.com/redis/mcp-redis.git redis-mcp-server, then pass your Redis connection via --url redis://... or environment variables. pip install and Docker are also supported.
Can it connect to Redis Cloud? Is it free?
Yes. Use a rediss:// connection string to reach Redis Cloud or any compatible instance. The MCP server itself is open source and free (MIT); local Redis and the Redis Cloud free tier cost nothing, and only larger hosted instances are billed.