The data layer for AI that actually ships

Whether you're building agents, copilots, or data-connected apps, CData handles the integration so you don't have to

0+
Customers
Hundreds
Of data sources
One
Data layer
30 min
To first answer

What are you building?

Three on-ramps. Pick the one closest to what you’re shipping today.

AI agent · 10 min

Scaffold an agent on live data

One npx command stands up a working LangChain, Google ADK, or Vercel AI SDK agent wired to Connect AI’s MCP server. Customize from there.

By AI surface · MCP reference

Python · 5 min

Build programmatic workflows with Python

DB-API 2.0. Connect, run SQL, get rows. Drop it into any Python app or notebook to read and write live data across hundreds of sources, with pandas, SQLAlchemy, and the tools you already use.

First query · Quick reference

CLI · Preview

Build apps with your AI coding agent

The CData CLI gives Cursor, Claude Code, and other AI coding assistants the schemas and connection wiring they need to generate accurate, runnable code against CData drivers, so the app your agent writes works the first time.

About the CLI

From prompt to action

Provision, fetch, and act—from a single prompt.

Connect AI’s Management MCP Server creates missing connections in-band. The Query MCP fetches your data. Your agents do the work. Watch the whole flow in the terminal.

Start the 5-min quickstart

Keep exploring

References, community, and fundamentals. Where to go after the quickstart.

Reference docs

Browse by language

Per-language references and dev guides for shipping with CData connectors.

Community

Get answers from CData devs

Ask questions, share patterns, and engage with CData developers and staff.

Fundamentals

New to CData drivers?

Learn how the unified SQL interface, relational models, and caching work.

Start building with live system access

Get the forever free developer edition to connect your app or agent to hundreds of sources.