Connect Claude to Redis

Inspect keys, values and server state on a Redis instance. Toolspoke puts 11 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Sandboxed CLI
Authentication: Connection URL
Actions exposed: 11
Cost per call (typical): 5 credits
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install Redis
Open the marketplace in your workspace, add Redis to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with connection url. Where to get one, and what it has to be able to reach, is the next section.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. Redis shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What Redis asks for

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 URLRequired: The number after the final slash is the database index. Use a user restricted to read commands where your Redis supports ACLs.; redis://default:[email protected]:6379/0

What Claude can do in Redis

11 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 11Reads
Writes: 0Writes
Destructive: 0Destructive

Reads

Fetches data and changes nothing.

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.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 11 actions above are the whole of it. A call to any other name is refused before it reaches Redis rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
It only reads: Every action here reads. Nothing this connector can do changes anything in Redis.
It reaches no further than your credential: Toolspoke holds no access to Redis of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from Redis: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Redis. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Redis's own rate limits. A call that Redis refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Redis?

11 named actions: 11 that only read. They include ping, server_info and database_size. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the Redis connector need?

Connection URL. The connector asks for connection url. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the Redis connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 11 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the Redis connector not do?

The 11 actions above are the whole of it. A call to any other name is refused before it reaches Redis rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. Every action here reads. Nothing this connector can do changes anything in Redis. Toolspoke holds no access to Redis of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Redis. An agent has to ask. Toolspoke does not retry, queue or back off around Redis's own rate limits. A call that Redis refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches Redis's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls Redis?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and the credits spent. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More database connectors

Browse all of them