Connect Claude to MySQL

Inspect schema, tables, indexes and keys on a MySQL or MariaDB database. Toolspoke puts 8 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: 8
Cost per call (typical): 5 credits
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install MySQL
Open the marketplace in your workspace, add MySQL 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. MySQL 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 MySQL 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: Use a read-only user where possible. The database in the path is the one every query runs against.; mysql://user:[email protected]:3306/mydb

What Claude can do in MySQL

8 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: 8Reads
Writes: 0Writes
Destructive: 0Destructive

Reads

Fetches data and changes nothing.

server_info
Server version, current user and the database this install is pointed at. The cheapest proof the credential works, and the health check.
list_tables
Tables and views in the connected database with their engine, estimated row count and size on disk. Row counts come from the information schema and are estimates for InnoDB, not exact counts. Call this before describe_table to learn a table name.
describe_table
Every column of one table with its type, nullability, default and key role. Use list_tables first for the name.
list_indexes
Indexes on one table, in key order, with their uniqueness and cardinality. Read this before explaining why a query is slow.
list_foreign_keys
Foreign keys declared in this database, both sides named, so a schema can be traversed without guessing at join columns.
list_databases
Databases this user can see. Informational only: every query runs against the database named in the connection URL, and this connector cannot switch.
run_query
Run a SELECT and return its rows. The session is opened read-only, so an INSERT, UPDATE or DDL statement is refused by the server; the statement is also checked here for being a single read before it is sent. The query is wrapped in an outer LIMIT, so a missing WHERE clause does not return a whole table by accident.
explain_query
The planner's chosen plan for a statement, without running it. Use it to explain a slow query before suggesting an index.

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 8 actions above are the whole of it. A call to any other name is refused before it reaches MySQL 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 MySQL.
It reaches no further than your credential: Toolspoke holds no access to MySQL 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 MySQL: 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 MySQL. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around MySQL's own rate limits. A call that MySQL refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in MySQL?

8 named actions: 8 that only read. They include server_info, list_tables and describe_table. 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 MySQL 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 MySQL connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 8 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 MySQL connector not do?

The 8 actions above are the whole of it. A call to any other name is refused before it reaches MySQL 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 MySQL. Toolspoke holds no access to MySQL 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 MySQL. An agent has to ask. Toolspoke does not retry, queue or back off around MySQL's own rate limits. A call that MySQL 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 MySQL'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 MySQL?

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