Set it up
- 1
Turn on Redis in your AI
In Claude: open Settings → Connectors and add Redis. In ChatGPT: Settings → Apps & Connectors.
- 2
Add it to your app once
Copy the short config below into your app. It just tells your AI where to find Redis.
- 3
Just ask
Tell it what you want in plain words — no special commands.
For example, say
“Show me the 20 most recently modified keys in my Redis database”
Need the exact config? Show it +
Add to your client
{
"mcpServers": {
"redis": {
"command": "uvx",
"args": ["--from", "redis-mcp-server@latest", "redis-mcp-server", "--url", "redis://localhost:6379/0"]
}
}
}Paste into your client's MCP configuration file.
Get the skill
A ready-made skill that teaches your AI agent to use Redis well. Redis' official skills for core, query, vector search and more.
npx skills add redis/agent-skills Quick skills
Copy one, paste it to your AI, watch it work.
Cache Inspection
“Show me all keys matching 'session:*' and tell me the TTL of the 5 most recent ones”
Targeted Cache Clearing
“Delete all keys matching 'user:123:*' to clear that user's cache”
Rate Limit Debugging
“What's the current value of the key 'ratelimit:ip:1.2.3.4'?”
In the wild
“Connected my readonly DB via MCP and the readonly key from my payment processor, re-attributed everything”
Good to know
- · Running KEYS * on a large production Redis can freeze the server — prefer SCAN
- · FLUSHDB and FLUSHALL wipe the entire database instantly — these should never be exposed to AI without guardrails
- · Connection strings include passwords — store them in env vars, not config files
When to use
- ✓ You're debugging cache behavior and want to inspect live keys
- ✓ You need to clear or expire specific keys during a deployment
- ✓ You're learning Redis data structures and want AI to explain what's stored
- ✓ You're investigating rate-limiting or session issues
When not to use
- × You use Memcached, KeyDB, or DynamoDB for caching (different protocol)
- × You want to give AI write access to production cache without review
- × You need Redis pub/sub streaming through the MCP (not its strength)
About
Imagine asking your AI: 'What keys are in my Redis cache that start with user:' or 'Clear all session keys older than an hour' — and it manages Redis for you. This server connects your AI to a Redis instance so it can read, write, and inspect keys, lists, sets, and streams through conversation.
The Redis MCP server provides AI assistants with access to Redis databases. Get and set values, work with Redis data structures (lists, sets, hashes, sorted sets), execute commands, and analyze cache contents — all through natural language.
Useful for debugging cache issues, analyzing session data, and understanding Redis usage patterns in development.
Workflows That Use Redis MCP
Works With
Also Consider
FAQ
What does Redis MCP do? +
Imagine asking your AI: 'What keys are in my Redis cache that start with user:' or 'Clear all session keys older than an hour' — and it manages Redis for you. This server connects your AI to a Redis instance so it can read, write, and inspect keys, lists, sets, and streams through conversation.
Do I need to know how to code? +
No. Turn it on in your AI's settings and ask in plain English — no terminal, no coding.
When should I use Redis MCP? +
Reach for it when you need to: You're debugging cache behavior and want to inspect live keys; You need to clear or expire specific keys during a deployment; You're learning Redis data structures and want AI to explain what's stored; You're investigating rate-limiting or session issues.
When should I avoid Redis MCP? +
Skip it when: You use Memcached, KeyDB, or DynamoDB for caching (different protocol); You want to give AI write access to production cache without review; You need Redis pub/sub streaming through the MCP (not its strength).
How do I install Redis MCP? +
In Claude Code, run: claude mcp add redis -- uvx --from redis-mcp-server@latest redis-mcp-server --url redis://localhost:6379/0. Copy-paste configs for Claude Desktop, Cursor, and Windsurf are at the top of this page.