Redis
Summary
Redis's official MCP server — read and write every Redis data structure, including vector search and streams.
Features
- Work with strings, hashes, lists, sets, sorted sets, and streams
- Vector search over Redis indexes
- Pub/sub and JSON document operations
Installation
Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.
Description
Redis's official MCP server gives an assistant natural-language access to a Redis instance across the full range of data structures rather than just get and set.
Coverage
- Core types. Strings, hashes, lists, sets, sorted sets, and their associated operations.
- Streams for event data, including consumer group inspection.
- JSON documents via RedisJSON.
- Vector search over Redis indexes, which makes it usable as the retrieval layer for an agent as well as the cache.
- Pub/sub for publishing and inspecting channels.
- Server introspection — memory usage, key counts, and configuration.
Where it earns its place
Redis is usually the least-documented part of a system: keys are created by application code and their conventions live in someone's head. Being able to ask what a key contains, what its TTL is, and how many of a pattern exist turns debugging a cache problem into a conversation.
Installed with uvx redis-mcp-server and configured through environment variables, with support for TLS, Redis Cloud, and cluster mode.
Related MCP Servers
DBHub
by Bytebase
A universal database MCP server — one integration for PostgreSQL, MySQL, SQL Server, SQLite, and MariaDB.
MongoDB
by MongoDB
MongoDB's official MCP server — query databases, explore schemas, and manage Atlas clusters from an AI client.
Upstash Redis
by Upstash
Run Redis commands against Upstash's serverless Redis over HTTP, with documentation search built in.
dbt
by dbt Labs
dbt Labs' official MCP server — explore project metadata, run dbt commands, and query the Semantic Layer.