Connect your data to Codex
Give OpenAI Codex CLI real-time database access for data-grounded coding sessions.
What Codex can do with Sequel
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.
Everything you can ask Codex about your data.
Ask in plain English. Sequel turns it into a query, runs it read-only, and Codex hands back the answer. No SQL, no dashboards, no CSV exports.
Connect Codex- What's the schema of our main database?
- Show me sample data from the `events` table
- How many active users do we have in the `users` table?
- Find all tables that reference `organization_id`
- What columns exist on the `subscriptions` table and what are their types?
Setup
Add Sequel to Codex
Drop the Sequel MCP server into Codex, then ask it anything about your connected data. Sequel is read-only by default and shows each query before it runs.
~/.codex/config.yaml
mcp_servers:
sequel:
type: http
url: https://api.sequel.sh/mcp
headers:
Authorization: "Bearer sql_your_api_key"Install
Install Sequel 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
- 1Run the command in your terminal. It writes the server to ~/.codex/config.toml.
- 2Run codex mcp login sequel and sign in in the browser.
- 3Start Codex and ask a question.
Data sources
Connect any source to Codex
PostgreSQL
Query your PostgreSQL database in plain English. No SQL required.
MySQL
Instant insights from your MySQL database. Ask in plain English.
ClickHouse
Real-time analytics on ClickHouse at any scale, in plain English.
BigQuery
Query petabytes of BigQuery data in plain English.
Google Sheets
Query, write, and manage Google Sheets with AI.
Google Analytics 4
Ask your GA4 data anything. No SQL, no dashboards.
Google Search Console
Unlock your SEO data with natural language. No exports, no pivot tables.
MCP Server
Connect any MCP-compatible server and query it with AI in seconds.
Stripe
Ask your Stripe data anything. MRR, churn, refunds — answered in plain English.
Polar
Ask your Polar revenue, subscriptions, and usage data anything — in plain English.
Dodo Payments
Ask questions about payments, subscriptions, refunds and payouts in plain English.
PostHog
Ask your PostHog product data anything — with HogQL under the hood.
Mixpanel
Conversational analytics on your Mixpanel events, funnels, and retention.
Amplitude
Query your Amplitude taxonomy, funnels, and dashboards in plain English.
HubSpot
Your AI analyst for HubSpot contacts, deals, tickets, and pipelines.
Ahrefs
Ask your Ahrefs SEO data anything: backlinks, keywords, and traffic.
Apollo.io
Ask your Apollo.io prospects, contacts, and accounts anything, in plain English.
Cloudflare D1
Ask your Cloudflare D1 database questions in plain English.
Instagram organic analytics — post engagement, reach, and audience insights in plain English.
Explore other AI agents
Claude
Use Claude to query your databases, explore schemas, and build analyses — all from one conversation.
Cursor
Query your databases and explore schemas without leaving your code editor.
ChatGPT
Connect ChatGPT to your databases and get data-backed answers in every conversation.
VS Code
Get database access inside VS Code Copilot without leaving your editor.
Windsurf
Give Windsurf's Cascade AI access to your databases — query data without leaving your editor.
Zed
Connect Zed's AI assistant to your databases for real-time data access while you code.
Gemini
Connect Google Gemini to your databases for grounded, data-backed answers.
Claude Code
Query your databases directly from the Claude Code CLI — without leaving your terminal.
OpenClaw
Turn your self-hosted OpenClaw agent into a data analyst that queries every source you've connected.
Hermes
Give Nous Research's Hermes agent read access to every database and marketing tool you've connected.
Grok Bot
Tell your Grok bot to add Sequel and it can query every database and marketing tool you've connected.
Muse
Give Meta's Muse one message and it builds its own connector to every source you've put in Sequel.
dots
Add Sequel once in ChatGPT and your dot can answer data questions on its own, day and night.
Frequently asked questions
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.
Put your data inside Codex
Connect in minutes — then ask across all your data, not just one source.