CData Code Assist MCP for API

Overview

The CData Code Assist MCP for API exposes API as a toolset accessible to large language models (LLMs), using the open Model Context Protocol (MCP). Each connector runs as a lightweight MCP server, enabling AI tools to discover, interpret, and invoke operations on live data — all through natural language.

This connector is designed specifically for tool-based, non-SQL interaction. LLMs use metadata provided by the server to understand and interact with API data safely, without requiring SQL queries or traditional prompt engineering.

Key Features

Allows for rapid development of data-connected applications using CData drivers.
Exposes API data to LLMs using the Model Context Protocol (MCP).
Supports secure, tool-based interactions — no SQL required.
Runs lightweight MCP server instances per connection.
Built-in support for popular authentication flows.
Seamless local integration with MCP clients.

The CData Code Assist MCP for API accelerates the development of data-connected applications using CData Drivers for JDBC, ADO.NET, and Python. Within AI coding tools, it enables schema discovery and SQL prototyping before driver code is written. Because CData Code Assist MCP shares the same codebase as the drivers themselves, all table names, column names, and supported SQL syntax are identical. Queries validated through CData Code Assist MCP can be used directly in your driver implementations.

Getting Started

See Getting Started for step-by-step instructions on installing the server, establishing a connection, and configuring an MCP client to access API data.

Using with AI Tools

See Using AI Tools to learn how popular AI tools connect to the CData Code Assist MCP and use tool metadata to interact with API through natural language requests.

Connection String Options

The Connection properties describe the various options that can be used to establish a connection.