MCP server · Data + databases
Redis MCP
Let agents read, write, search and manage Redis data structures through Redis's official MCP server.
Quick verdict
It exposes a broad first-party Redis tool set without asking an agent to synthesise raw Redis commands or embedding a bespoke database client.
- MaintainerRedis (official)
- Security scopeRead-write
- Transportsstdio
- Install channelpypi · redis-mcp-server
- EvidenceSource Validated
- LicenseMIT · Open source
Redis's official server for agent access to strings, hashes, lists, sets, sorted sets, streams, JSON documents, pub/sub and vector search. It runs locally over stdio and connects to whichever Redis deployment you point it at — local, self-hosted or managed — so the connection's Redis ACL, not the server, sets its real authority.
Install Redis MCP
uvx --from redis-mcp-server@latest
{
"mcpServers": {
"redis-mcp": {
"command": "uvx",
"args": ["--from", "redis-mcp-server@latest", "redis-mcp-server", "--url", "redis://localhost:6379/0"]
}
}
}Runs with uvx (uv); an official Docker image is also published. Authentication can come from a Redis URI, individual connection parameters, TLS client material, Redis ACLs, or the documented Entra ID flow for Azure Managed Redis.
Credentials
| Name | Required | What it is for |
|---|---|---|
REDIS_USERNAME | Optional | Optional Redis ACL username for authenticated deployments. |
REDIS_PWD | Optional | Optional Redis password. Prefer a dedicated least-privilege ACL user over an administrator credential. |
REDIS_ENTRAID_CLIENT_SECRET | Optional | Optional client secret for the documented Entra ID service-principal flow with Azure Managed Redis. |
Verified configurations
Not run by us yet. This profile is Source Validated: the install channel, config entry, credentials and license were checked against the source and upstream metadata, but no configuration has been installed, discovered and executed in a recorded environment. When one is, it appears here with the eight scope dimensions below.
Best for
Stateful agent workflows needing structured caching, queues, streams, JSON documents or vector search in an existing Redis deployment.
Why use it
It exposes a broad first-party Redis tool set without asking an agent to synthesise raw Redis commands or embedding a bespoke database client.
Tradeoffs
The tool surface includes writes and deletions across many Redis types — documented tools remove keys, delete stream entries and destroy consumer groups — so a broadly privileged connection can change production state fast. The configuration published here assumes an isolated, unauthenticated Redis on loopback and is deliberately not a production setup: use a dedicated database or ACL user, TLS for anything remote, and a throwaway fixture for testing.
Upstream state
pypi package published · repository active · in the official MCP Registry (active). Lifecycle is derived from a committed upstream snapshot at build time, never authored by hand.
Official MCP Registry name: io.github.redis/mcp-redis
Editorial review
Grade B — Source Validated. Re-review is due by 2027-02-15. Config entries, credential names and package status can change upstream; verify against the source repository before granting an agent access.
Sources
Related MCP servers
- Semgrep MCPRun Semgrep security scans through MCP so coding agents can analyze source code for vulnerabilities locally.
- Supabase MCPSupabase's official MCP server: lets an agent manage tables, run SQL, read logs and deploy Edge Functions in your project — scope it read-only.
- ClickHouse MCPQuery ClickHouse databases through the official MCP server, with read-only SQL enforced by default and separate write opt-ins.