# Redis (MCP Server)

> Official natural-language interface for managing and searching Redis data

- Type: MCP server
- Publisher: Redis (official)
- Categories: Data & Analytics, Development
- Website: https://github.com/redis/mcp-redis
- Source: https://github.com/redis/mcp-redis
- Transport: stdio
- Launch command: uvx --from redis-mcp-server@latest redis-mcp-server --url redis://localhost:6379/0
- Sign-in: none
- Environment variables: REDIS_HOST, REDIS_PORT, REDIS_PWD
- GitHub stars: 628
- Listed: 2025-04-02

## About

Official Redis MCP server for managing data in Redis, including strings, hashes, lists, sets, sorted sets, streams, JSON and pub/sub. Also supports vector indexes and vector search via the query engine. Distributed on PyPI as redis-mcp-server.

## Install

1. **Add the server to Codex**

   Codex CLI:

   ```bash
   codex mcp add redis --env REDIS_HOST=YOUR_REDIS_HOST --env REDIS_PORT=YOUR_REDIS_PORT --env REDIS_PWD=YOUR_REDIS_PWD -- uvx --from redis-mcp-server@latest redis-mcp-server --url redis://localhost:6379/0
   ```

   config.toml:

   ```toml
   [mcp_servers.redis]
   command = "uvx"
   args = ["--from", "redis-mcp-server@latest", "redis-mcp-server", "--url", "redis://localhost:6379/0"]
   
   [mcp_servers.redis.env]
   REDIS_HOST = "YOUR_REDIS_HOST"
   REDIS_PORT = "YOUR_REDIS_PORT"
   REDIS_PWD = "YOUR_REDIS_PWD"
   ```

   Agents SDK:

   ```python
   from agents import Agent, Runner
   from agents.mcp import MCPServerStdio
   
   async with MCPServerStdio(
       name="Redis",
       params={"command": "uvx", "args": ["--from", "redis-mcp-server@latest", "redis-mcp-server", "--url", "redis://localhost:6379/0"]},
   ) as server:
       agent = Agent(name="Assistant", mcp_servers=[server])
       result = await Runner.run(agent, "Cache this API response under key user:42 for 10 minutes")
       print(result.final_output)
   ```

## Tools

- `set`
- `get`
- `hset`
- `hgetall`
- `lpush`
- `lrange`
- `sadd`
- `zadd`
- `xadd`
- `json_set`
- `vector_search_hash`
- `scan_keys`

## Example prompts

- "Cache this API response under key user:42 for 10 minutes"
- "Show me all keys matching session:*"
- "Add an event to the orders stream"
- "Create a vector index and search for similar products"

## Also available as

- plugin: [Redis](https://chatgptplugins.directory/plugins/redis.md)

## Related

- [Chrome DevTools MCP](https://chatgptplugins.directory/mcp/chrome-devtools.md): Let coding agents control and debug a live Chrome browser
- [Playwright MCP](https://chatgptplugins.directory/mcp/playwright.md): Browser automation for agents via Playwright accessibility snapshots
- [GitHub](https://chatgptplugins.directory/mcp/github.md): Manage repos, issues, pull requests and Actions from your AI agent
- [Context7](https://chatgptplugins.directory/mcp/context7.md): Pull up-to-date, version-specific library docs into your coding agent
- [Supabase](https://chatgptplugins.directory/mcp/supabase.md): Manage Supabase databases, migrations, edge functions and logs
- [Stripe](https://chatgptplugins.directory/mcp/stripe.md): Query and act on your Stripe account and search Stripe docs from any agent

---
Source: https://chatgptplugins.directory/mcp/redis · Index: https://chatgptplugins.directory/llms.txt · Independent and community-run. Not affiliated with or endorsed by OpenAI. ChatGPT is a trademark of OpenAI.