Redis MCP in Claude Code

Quick answer: Install the Redis MCP server with npx -y @modelcontextprotocol/server-redis redis://default:pw@localhost:6379, add the JSON block below to ~/.claude/settings.json, restart Claude Code, and run /mcp to confirm the connection. Setup runs about 5 minutes on a fresh machine, verified on @modelcontextprotocol/server-redis as of April 15, 2026.

The Redis MCP server exposes a Redis client as a tool surface for Claude Code. After setup, the model can run GET, SET, KEYS, TTL, INFO, and the full command vocabulary against your Redis instance. Handy for inspecting cache state, debugging session storage, or cleaning up stuck keys without swapping to redis-cli.

This guide covers what you get after the wiring is done, the exact config, verification steps, prompt patterns that tend to work well, and the 4 issues that trip people up most often in the first week.

What you get when it is connected

Once the Redis server is attached, Claude Code can call the server tools from inside any conversation. You do not invoke the tools by hand. When you ask Claude a question the model decides which tool to call and parses the response for you. For teams that live inside Redis day to day, this replaces dozens of context switches per week with a single line in chat.

The server speaks the full Redis command set through a general execute tool plus a few convenience wrappers (get, set, keys, info). Pipelining is supported internally, so multi-key reads come back in a single round trip when the model batches them. TLS connections work with the rediss:// URL scheme.

Prerequisites

A Redis 6+ instance reachable from your machine. A connection URL including password if one is set. Node 20 or later on the host running Claude Code.

If you use a version manager like nvm or asdf for Node, confirm the version Claude Code inherits. Open a terminal, run node -v, and note the output. Claude Code uses the Node it sees on PATH at launch, so a shell profile that sets the right version is the reliable path.

Install via npx

Run the package once with npx to verify it starts cleanly:

npx -y @modelcontextprotocol/server-redis redis://default:pw@localhost:6379

The first run downloads the package (a few MB) and starts the server on stdio. The server does not print much on success - it waits for MCP protocol messages on stdin. Press Ctrl-C to stop it. The actual runtime setup happens through Claude Code itself in the next step.

If the install fails with a network error, your npm registry may be blocked. Set npm config set registry https://registry.npmjs.org and retry. Behind a corporate proxy, also set HTTP_PROXY and HTTPS_PROXY in your shell.

Add the config block to ~/.claude/settings.json

Open ~/.claude/settings.json in your editor. If the file does not exist yet, create it with {} as the starting content. Add an mcpServers object with an entry for this server:

{
  "mcpServers": {
    "redis": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-redis",
        "redis://default:pw@localhost:6379"
      ]
    }
  }
}

Save the file. If you already have other MCP servers defined, merge the new entry into the existing mcpServers object rather than replacing it.

Restart Claude Code fully (quit and reopen, not just close the window). The server is spawned lazily on the first tool call in a session, not at launch, but the config is read once per Claude Code start.

Verify the connection

Open a new Claude Code session and type /mcp at the prompt. You should see the server listed with a green or connected indicator. If it shows as failed, click into it for the stderr output - the error message usually points at the problem directly (bad token, wrong path, missing Node).

Run a trivial first prompt to confirm round trips work. Good smoke tests:

• For read servers: ask for a list of whatever resource type it exposes.
• For write servers: ask for a describe on a known resource first, then try a safe write on a test resource.

If the first prompt works, the wiring is done. From here on you interact with the server purely through normal prompts in Claude Code.

Example prompts that work well

Here are prompts that tend to get good responses once the server is attached:

• List all keys matching the pattern session:* and tell me how many there are and what their TTLs look like.
• Get the value of the key user:42:profile and pretty-print it as JSON.
• Set the key feature_flag:new_pricing to true with a TTL of 3600 seconds.
• Run INFO memory and tell me how much memory the instance is using.
• Find any keys in the cache namespace that have no TTL and list them.
• Delete every key matching temp:2026-03-* and tell me how many were removed.

Claude will chain tool calls on its own when the prompt implies several steps. For a summarize-then-write flow the model will often call read tools first, then a single write tool at the end. If a prompt keeps burning tool calls, narrow it: specify the resource ID, the time range, or the exact field you want rather than asking Claude to scan everything.

Environment variable security

The connection URL is passed as a positional argument, which means the password is inline. For production, use an env var alternative: set REDIS_URL in your shell profile, then reference it in the Claude config with shell expansion if your deployment supports it. On Windows or when expansion does not work, use a local password file and an unprivileged reader user.

A general rule across every MCP server: never paste secrets directly into settings.json that lives in a shared or git-tracked directory. Keep the actual secret values in your shell profile (~/.zshrc, ~/.bashrc, or a 1Password-cli helper), export them at shell start, and reference the variable names from the Claude config. That way the secret stays on your machine and the config file is safe to share with teammates.

On macOS, terminals launched from Spotlight or from the Dock both inherit the shell profile. If you launch Claude Code from a GUI shortcut that does not go through a shell, env vars may not propagate - launch from a terminal instead.

Troubleshooting

Tool calls return ECONNREFUSED. Redis is not reachable at the URL. Try redis-cli -u $REDIS_URL ping from the same machine. If that fails, check firewall rules and make sure Redis is binding to the expected interface.

Commands fail with NOAUTH Authentication required. The connection URL is missing the password. Format it as redis://username:password@host:port, or if you use the default user, redis://default:password@host:port.

KEYS command blocks on a large database. KEYS scans the whole keyspace and blocks other clients on big Redises. Ask Claude to use SCAN with a MATCH pattern and a COUNT hint instead. It gives the same result with far less impact.

Large values get truncated in responses. The server caps tool response size at around 1 MB. For huge values, ask Claude to request a substring or specific field rather than the full blob.

For any issue not listed here, the first step is /mcp inside Claude Code to see the current status and any recent stderr from the server. The second step is running the exact npx command from your terminal to see if the server starts cleanly outside Claude Code. Between those two checks, most problems become obvious within a minute.

Next steps

Once the Redis server is attached and verified, the useful next move is writing a short prompt template you keep in your notes. List the 3 or 4 prompts you run most often against this server, and paste them into Claude Code when needed. Over a few weeks you build a personal command library that gets real work done without typing much.

For team projects, commit a .mcp.json at the repo root with the same structure. Everyone on the team gets the server wired up automatically on first open, and individual secrets stay in shell profiles. That is the setup pattern that scales past a single developer.