Codex
Dinobase integrates with Codex via CLI. Once connected, Codex’s AI agent can query all your synced business data while you code.
Install
Section titled “Install”curl -fsSL https://dinobase.ai/install.sh | bash -s -- codex
# Or if Dinobase is already installed:dinobase install codexInstalls Dinobase via uv, runs dinobase init, and writes CLI usage instructions to ~/.codex/AGENTS.md. Then add your connectors:
dinobase add stripe --api-key sk_test_...dinobase add hubspot --api-key pat-...dinobase syncSee Connectors for the full list of 100+ supported connectors, and Syncing & Scheduling for background sync options.
Codex can run shell commands directly, so no MCP configuration is needed. Just ask questions about your data and Codex will run dinobase info, dinobase describe stripe.customers, and dinobase query "SELECT ..." to answer them.
To re-run the setup step: dinobase install codex (safe to run multiple times — replaces the existing block).
How it works
Section titled “How it works”The agent will:
- Run
dinobase infoto discover available data - Run
dinobase describe <table>to understand columns and types - Run
dinobase query "<sql>"to execute SQL (DuckDB dialect) - For mutations (UPDATE/INSERT),
queryreturns a preview — the agent runsdinobase confirm <id>to execute
Alternative: MCP server
Section titled “Alternative: MCP server”If you prefer MCP, run dinobase mcp-config codex to get the JSON config, then add it to your Codex MCP configuration.
Available CLI commands
Section titled “Available CLI commands”| Command | Description |
|---|---|
dinobase info | Database overview — connectors, tables, row counts |
dinobase describe <table> | Table schema, column types, and sample data |
dinobase query "<sql>" | Execute SQL queries (DuckDB dialect) |
dinobase refresh [connector] | Re-sync a connector to get fresh data |
dinobase confirm <id> | Execute a pending mutation |
dinobase cancel <id> | Cancel a pending mutation |
Next steps
Section titled “Next steps”- Getting Started — Full setup walkthrough
- Connectors — Add your business data
- Querying Data — SQL patterns and cross-connector joins
- Syncing & Scheduling — Keep data fresh
- Schema Annotations — Add context for AI agents
- MCP Integration — How the MCP server works
- MCP Tools Reference — Detailed tool schemas