Connect Redis to Claude Code

Inspect keys, values and server state on a Redis instance. Add Toolspoke to Claude Code once and it can use 11 Redis actions. Your Redis credential stays in Toolspoke, and you choose which actions Claude Code may call.

Set it up in Claude Code

Three steps, the first one once for every toolkit you will ever add.

  1. Add Toolspoke to Claude Code

    Run it in your project, then /mcp to sign in

    claude mcp add --transport http toolspoke https://toolspoke.com/mcp

    The sign-in opens in your browser, and Toolspoke asks you to approve it.

  2. Install Redis and connect it

    Add Redis to a project in your Toolspoke workspace.

    Connection URL. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

    Connection URL
    The number after the final slash is the database index. Use a user restricted to read commands where your Redis supports ACLs.
  3. Choose what Claude Code may do

    All 11 actions only read, and any of them can be switched off for a project.

What you can ask Claude Code for

A few of the Redis actions that only read, so they are safe to try first.

  • Answer PONG if the instance is reachable and the credential is accepted
  • How many keys are in the selected database
  • Walk the keyspace a page at a time, optionally filtering by pattern
  • Read a string key's value

What Claude Code can do in Redis

11 actions read.

Reads

  • Ping

    Answer PONG if the instance is reachable and the credential is accepted. Costs nothing and takes no arguments, which is why it is the health check.

  • Server info

    Server version, uptime, memory use, connected clients and keyspace sizes, the INFO sections worth reading first when something is slow.

  • Database size

    How many keys are in the selected database. Cheap, and the number to check before scanning.

  • Scan keys

    Walk the keyspace a page at a time, optionally filtering by pattern. Returns a cursor to pass back for the next page; a cursor of 0 means the walk is finished. Preferred over KEYS, which blocks the server for the length of the scan.

  • Get key

    Read a string key's value. Use key_type first when the type is unknown, this returns an error rather than a value for a hash, list or set.

  • Key type

    What kind of value a key holds: string, list, set, zset, hash or stream. Call this before choosing between get_key, list_range, hash_fields and set_members.

  • Key ttl

    Seconds until a key expires. -1 means it never expires, -2 means it does not exist.

  • Hash fields

    Every field and value of a hash key.

  • List range

    A slice of a list key. Indexes are zero-based and may be negative, so -1 is the last element.

  • Set members

    Every member of a set key.

  • Memory usage

    How many bytes one key occupies, including its overhead. Use it to find what is filling an instance.

Redis in Claude Code: questions

Does Claude Code see my Redis credential?

No. The credential is stored encrypted in Toolspoke, and the gateway adds it to each call. Claude Code only ever talks to Toolspoke, and the dashboard shows the last four characters of the credential and nothing more.

Will 11 actions crowd Claude Code's context?

No. Toolspoke shows Claude Code five bridge tools, plus a guide where a toolkit has one, and Claude Code searches for the Redis action it needs when it needs it. Adding more toolkits does not add more tools to its list.

Can I add it once for every project?

Yes. Add --scope user to the command and Claude Code keeps Toolspoke in every project on this machine. Without it, the server is added to the project you ran the command in.

What does it cost?

Tool calls are free on every plan. Redis runs in a sandbox, so a call bills the sandbox time it uses.

Try Redis in Claude Code

Free to start, and tool calls cost nothing on any plan.