How to Connect MySQL to Codex

Query your MySQL data directly from Codex using Sequel’s MCP server. Ask questions in plain English, with no SQL, no dashboards, and no context switching.

Short answer

Connect MySQL to Sequel, then add Sequel's MCP server to Codex using the config on this page. Codex can then query your live MySQL data in plain English, with no connector code and no CSV exports. Both steps take a few minutes.

Example prompts

Everything you can ask Codex about your MySQL data.

Ask in plain English — Sequel translates it into a MySQL query, runs it, and Codex hands back the answer. No SQL, no dashboards, no CSV exports.

What you can ask Codex
  • Show me total sales by product category last quarter
  • Which customers haven't placed an order in 90 days?
  • What's the average session duration by user cohort?
  • Find all orders where payment status is pending for more than 7 days
  • Show me signups by day for the past 30 days

How it works

Three steps to get started

1

Connect MySQL to Sequel

In your Sequel dashboard, go to Connections and add MySQL. Sequel handles authentication and schema discovery automatically.

2

Add Sequel to the agent

Copy the Sequel MCP configuration into Codex's settings file (shown below). Swap in your API key from Settings → API Keys.

3

Ask Codex about your data

Restart Codex and start asking questions. "Show me total sales by product category last quarter" — and get a real answer backed by live MySQL data.

Why Codex

What Codex does with your MySQL data

Grounded answers from real data

Codex with Sequel queries your actual databases before generating code or explanations. Every schema reference, column name, and data shape is verified against what's really there.

Terminal-native data access

No context switching — Codex can pull database data mid-session to inform code generation, write migrations based on actual schemas, and validate assumptions without leaving the terminal.

Agentic data workflows

Codex's multi-step agent can chain Sequel tool calls together: discover schema, sample data, run analysis, then generate code — all in one automated flow.

Configuration

Add Sequel to Codex

Place this in ~/.codex/config.yaml and replace sql_your_api_key with a key from Settings → API Keys.

~/.codex/config.yaml

mcp_servers:
  sequel:
    type: http
    url: https://api.sequel.sh/mcp
    headers:
      Authorization: "Bearer sql_your_api_key"

Install

Install MySQL MCP in Codex

Pick your app and Sequel installs itself: a one-click link where the client supports it, that client’s own few steps where it doesn’t. Every route signs in with your Sequel account over OAuth, so there is no API key to copy and nothing to keep in sync.

Already have an MCP client?

https://api.sequel.sh/mcp

Add it as a remote (streamable HTTP) server and sign in when prompted. Skills come with it; nothing else to install. Manual setup per client

Add Sequel to Codex

Terminal

codex mcp add sequel --url https://api.sequel.sh/mcp
  1. 1Run the command in your terminal. It writes the server to ~/.codex/config.toml.
  2. 2Run codex mcp login sequel and sign in in the browser.
  3. 3Start Codex and ask a question.

Frequently asked questions

How do I connect MySQL to Codex?

You need two things: (1) connect MySQL to Sequel in your Sequel dashboard under Connections, and (2) add the Sequel MCP config to Codex using the setup shown above. Once both are done, Codex can query your MySQL data directly.

What MySQL data can Codex access?

Codex can access any data available through your MySQL connection in Sequel. Use Sequel's search tool to discover available metrics and dimensions, then execute queries to pull the data you need.

Is my MySQL data sent to Codex's servers?

Query results are returned to Codex as context within your conversation. Only the data you explicitly ask about is retrieved. Sequel never stores your query results permanently — they exist only for the duration of the tool call.

Do I need a Sequel account?

Yes. You need a Sequel account to connect MySQL and generate an API key. Sign up free at sequel.sh — no credit card required. Then create a connection to MySQL and generate an API key from Settings → API Keys.

Can I connect multiple MySQL accounts?

Yes. Sequel supports multiple connections of the same type. If you have multiple MySQL accounts or properties, add each as a separate connection in Sequel. Codex will be able to query all of them.

How do I configure Sequel for Codex CLI?

Add the Sequel MCP server to ~/.codex/config.yaml as shown above. Create the file if it doesn't exist. Replace `sql_your_api_key` with a real key from Settings → API Keys, then restart Codex.

Does Codex CLI support HTTP MCP servers?

Yes. Codex CLI supports MCP over HTTP (Streamable HTTP transport). The `type: http` field in the config tells Codex to use this transport when connecting to Sequel.

Can I limit which databases Codex can access?

Sequel MCP is scoped to your organization's connected data sources. You can create separate API keys for different environments and revoke them at any time from Settings → API Keys.

Is this the same as the original OpenAI Codex model?

No — Codex CLI is OpenAI's agentic terminal coding tool, separate from the original Codex language model. It uses the latest OpenAI models (GPT-4o and o-series) with MCP tool support.

How do I connect my MySQL database?

Click 'New Connection', select MySQL, and enter your host, port, database name, username, and password. Sequel tests the connection before saving.

Which MySQL versions are supported?

Sequel supports MySQL 5.7 and above, including MySQL 8.x. MariaDB 10.3+ is also compatible.

Can Sequel write to my database?

No. Sequel is read-only by default. It will never execute INSERT, UPDATE, DELETE, or DDL statements unless you explicitly request and confirm it.

Can I connect a managed MySQL instance?

Yes. PlanetScale, AWS RDS, Google Cloud SQL, and other managed MySQL providers work. You may need to allowlist Sequel's IP in your provider's firewall settings.

Connect MySQL to Codex today

Sign up free, connect your data sources, and start querying in minutes.